Computer-aided detection of early neoplastic lesions in Barrett’s esophagus

Sommen, Fons van der; Zinger, Svitlana; Curvers, Wouter L.; Bisschops, Raf; Pech, Oliver; Weusten, Bas L.; Bergman, Jacques; Schoon, Erik J.

doi:10.1055/s-0042-105284

Cited by 153 publications

(125 citation statements)

References 18 publications

Supporting

Mentioning

124

Contrasting

Unclassified

Order By: Relevance

“…Experiment 3 : Leave-One-Patient-Out cross-validation (LOPO-CV) is applied to compare the four detection methods. Table 3 demonstrates the results from LOPO-CV experiment in addition to a comparison with two of state-of-the-art (Mendel et al [20] and Sommen et al [16]) methods that use the same dataset. The results of the three experiments will be discussed further in the following section.…”

Section: Resultsmentioning

confidence: 99%

“…For a fair evaluation, we employ the same validation method LOPO-CV. Firstly, the sensitivity was evaluated, and the SSD achieved the highest performance among the four deep learning methods and surpassed the results of [20] by 2% and [16] by 10%. Also, the Faster R-CNN outperformed against [16] by 2%.…”

Section: Discussionmentioning

confidence: 96%

“…As a further study, a comparison of the results with other state-of-the-art models provided by Mendel et al [20] and Sommen et al [16] is illustrated in Table 3. For a fair evaluation, we employ the same validation method LOPO-CV.…”

Section: Discussionmentioning

confidence: 98%

“…Using a Leave-One-Patient-Out Cross-Validation (LOPO-CV) approach the experiments had an 85.7% accuracy compared to the annotation of the specialist with a recall of 0.95 and precision of 0.75 using the SVM classifier on the extracted gabor and color features. More tests were conducted in [16] with the same model on a more substantial dataset that resulted in a sensitivity of 0.86 and a specificity of 0.87 when using SVM and 0.90 and 0.75 for the precision when classified using the Random forest in [17]. …”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Early esophageal adenocarcinoma detection using deep learning methods

Ghatwary

Zolgharni

2019

Int J CARS

View full text Add to dashboard Cite

PurposeThis study aims to adapt and evaluate the performance of different state-of-the-art deep learning object detection methods to automatically identify esophageal adenocarcinoma (EAC) regions from high-definition white light endoscopy (HD-WLE) images.MethodSeveral state-of-the-art object detection methods using Convolutional Neural Networks (CNNs) were adapted to automatically detect abnormal regions in the esophagus HD-WLE images, utilizing VGG’16 as the backbone architecture for feature extraction. Those methods are Regional-based Convolutional Neural Network (R-CNN), Fast R-CNN, Faster R-CNN and Single-Shot Multibox Detector (SSD). For the evaluation of the different methods, 100 images from 39 patients that have been manually annotated by five experienced clinicians as ground truth have been tested.ResultsExperimental results illustrate that the SSD and Faster R-CNN networks show promising results, and the SSD outperforms other methods achieving a sensitivity of 0.96, specificity of 0.92 and F-measure of 0.94. Additionally, the Average Recall Rate of the Faster R-CNN in locating the EAC region accurately is 0.83.ConclusionIn this paper, recent deep learning object detection methods are adapted to detect esophageal abnormalities automatically. The evaluation of the methods proved its ability to locate abnormal regions in the esophagus from endoscopic images. The automatic detection is a crucial step that may help early detection and treatment of EAC and also can improve automatic tumor segmentation to monitor its growth and treatment outcome.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 96%

Section: Discussionmentioning

confidence: 98%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Early esophageal adenocarcinoma detection using deep learning methods

Ghatwary

Zolgharni

2019

Int J CARS

View full text Add to dashboard Cite

show abstract

“…This implies automated lesion measurement is feasible, and MLAs could eventually replace or drastically reduce the workload of valuable human resources. In a recent study, van der Sommen et al 14 detailed collaboration between IT engineers and clinicians to develop a CAD algorithm for diagnosis of early neoplasia in Barrett’s esophagus, with good results. An advantage of the method presented in this study over previous automated measurement approaches is its suitability for a variety of lesion types.…”

Section: Discussionmentioning

confidence: 99%

KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes

et al. 2017

View full text Add to dashboard Cite

Background and aims Capsule endoscopy (CE) has revolutionized small-bowel (SB) investigation. Computational methods can enhance diagnostic yield (DY); however, incorporating machine learning algorithms (MLAs) into CE reading is difficult as large amounts of image annotations are required for training. Current databases lack graphic annotations of pathologies and cannot be used. A novel database, KID, aims to provide a reference for research and development of medical decision support systems (MDSS) for CE. Methods Open-source software was used for the KID database. Clinicians contribute anonymized, annotated CE images and videos. Graphic annotations are supported by an open-access annotation tool (Ratsnake). We detail an experiment based on the KID database, examining differences in SB lesion measurement between human readers and a MLA. The Jaccard Index (JI) was used to evaluate similarity between annotations by the MLA and human readers. Results The MLA performed best in measuring lymphangiectasias with a JI of 81 ± 6 %. The other lesion types were: angioectasias (JI 64 ± 11 %), aphthae (JI 64 ± 8 %), chylous cysts (JI 70 ± 14 %), polypoid lesions (JI 75 ± 21 %), and ulcers (JI 56 ± 9 %). Conclusion MLA can perform as well as human readers in the measurement of SB angioectasias in white light (WL). Automated lesion measurement is therefore feasible. KID is currently the only open-source CE database developed specifically to aid development of MDSS. Our experiment demonstrates this potential.

show abstract

Identification of Barrett's neoplasia: Beyond Seattle protocol

Wang

2022

Adv in Digestive Medicine

View full text Add to dashboard Cite

Computer-aided detection of early neoplastic lesions in Barrett’s esophagus

Cited by 153 publications

References 18 publications

Early esophageal adenocarcinoma detection using deep learning methods

Early esophageal adenocarcinoma detection using deep learning methods

KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes

Identification of Barrett's neoplasia: Beyond Seattle protocol

Contact Info

Product

Resources

About