Deep learning assistance for the histopathologic diagnosis of Helicobacter pylori

Zhou, Sharon; Marklund, Henrik; Bláha, Ondřej; Desai, Manisha; Martin, Brock A.; Bingham, David; Berry, Gerald J.; Gomulia, Ellen; Ng, Andrew Y.; Shen, Jeanne

doi:10.1016/j.ibmed.2020.100004

Cited by 15 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, we observed that AI-attributable false alarms misled the pathologists on negative results, reducing the specificity from 94% to 84%. This phenomenon was also observed in a study by Zhou et al 31 ., in which AI-attributable false alarms reduced the specificity corresponding to the classification of cases negative for H. pylori (OR = 0.435). Notably, regarding positive LN images, the significantly improved sensitivity and interrater stability suggest that pathologists can reach a greater consensus in clinical practice with AI assistance.…”

Section: Discussionsupporting

confidence: 85%

“…reported that AI assistance in the classification of liver cancer significantly improved the accuracy ( P = 0.045, odds ratio [OR] = 1.499). The model developed by Zhou et al 31 . significantly shortened the time taken to review Helicobacter pylori –positive cases ( P = 0.003) and significantly increased the sensitivity with which they were identified (OR = 13.37).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep neural network trained on gigapixel images improves lymph node metastasis detection in clinical settings

Huang

Chen²,

Lan

et al. 2022

Nat Commun

View full text Add to dashboard Cite

The pathological identification of lymph node (LN) metastasis is demanding and tedious. Although convolutional neural networks (CNNs) possess considerable potential in improving the process, the ultrahigh-resolution of whole slide images hinders the development of a clinically applicable solution. We design an artificial-intelligence-assisted LN assessment workflow to facilitate the routine counting of metastatic LNs. Unlike previous patch-based approaches, our proposed method trains CNNs by using 5-gigapixel images, obviating the need for lesion-level annotations. Trained on 5907 LN images, our algorithm identifies metastatic LNs in gastric cancer with a slide-level area under the receiver operating characteristic curve (AUC) of 0.9936. Clinical experiments reveal that the workflow significantly improves the sensitivity of micrometastasis identification (81.94% to 95.83%, P < .001) and isolated tumor cells (67.95% to 96.15%, P < .001) in a significantly shorter review time (−31.5%, P < .001). Cross-site evaluation indicates that the algorithm is highly robust (AUC = 0.9829).

show abstract

Section: Discussionsupporting

confidence: 85%

Section: Discussionmentioning

confidence: 99%

Deep neural network trained on gigapixel images improves lymph node metastasis detection in clinical settings

Huang

Chen²,

Lan

et al. 2022

Nat Commun

View full text Add to dashboard Cite

show abstract

“…These objects may be of different kinds and identified at different scales. For example, determining whether a slide contains evidence of invasive primary tumour [7], or metastatic tumour [8], or Helicobacter pylori infection [9] are all primarily detection tasks. Often, what is detected needs to also be classified; for example, nuclei might be classified according to different cell types, and this used to determine metrics predictive of therapeutic response, such as the relative proportions of lymphocytes and tumour cells [10].…”

Section: Approaches To Digital Pathology Analysismentioning

confidence: 99%

Developing image analysis methods for digital pathology

Bankhead

2022

The Journal of Pathology

View full text Add to dashboard Cite

The potential to use quantitative image analysis and artificial intelligence is one of the driving forces behind digital pathology. However, despite novel image analysis methods for pathology being described across many publications, few become widely adopted and many are not applied in more than a single study. The explanation is often straightforward: software implementing the method is simply not available, or is too complex, incomplete, or dataset‐dependent for others to use. The result is a disconnect between what seems already possible in digital pathology based upon the literature, and what actually is possible for anyone wishing to apply it using currently available software. This review begins by introducing the main approaches and techniques involved in analysing pathology images. I then examine the practical challenges inherent in taking algorithms beyond proof‐of‐concept, from both a user and developer perspective. I describe the need for a collaborative and multidisciplinary approach to developing and validating meaningful new algorithms, and argue that openness, implementation, and usability deserve more attention among digital pathology researchers. The review ends with a discussion about how digital pathology could benefit from interacting with and learning from the wider bioimage analysis community, particularly with regard to sharing data, software, and ideas. © 2022 The Author. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

show abstract

“…Klein et al [ 82 ] published a DL algorithm for automatic H. pylori screening in Giemsa stains, with a sensitivity of 100% and a specificity of 66%[ 82 ]. In parallel, Zhou et al [ 83 ] used a CNN to assist pathologists in the detection of H. pylori cells in H&E-stained WSI, but failed to demonstrate significant improvements in diagnostic accuracy and turnaround times in comparison with unassisted case studies[ 83 ].…”

Section: Applications Of Ai In Gi Pathologymentioning

confidence: 99%

Role of artificial intelligence in multidisciplinary imaging diagnosis of gastrointestinal diseases

Berbís¹,

Aneiros‐Fernández²,

Olivares³

et al. 2021

WJG

View full text Add to dashboard Cite

The use of artificial intelligence-based tools is regarded as a promising approach to increase clinical efficiency in diagnostic imaging, improve the interpretability of results, and support decision-making for the detection and prevention of diseases. Radiology, endoscopy and pathology images are suitable for deep-learning analysis, potentially changing the way care is delivered in gastroenterology. The aim of this review is to examine the key aspects of different neural network architectures used for the evaluation of gastrointestinal conditions, by discussing how different models behave in critical tasks, such as lesion detection or characterization ( i.e. the distinction between benign and malignant lesions of the esophagus, the stomach and the colon). To this end, we provide an overview on recent achievements and future prospects in deep learning methods applied to the analysis of radiology, endoscopy and histologic whole-slide images of the gastrointestinal tract.

show abstract

Deep learning assistance for the histopathologic diagnosis of Helicobacter pylori

Cited by 15 publications

References 17 publications

Deep neural network trained on gigapixel images improves lymph node metastasis detection in clinical settings

Deep neural network trained on gigapixel images improves lymph node metastasis detection in clinical settings

Developing image analysis methods for digital pathology

Role of artificial intelligence in multidisciplinary imaging diagnosis of gastrointestinal diseases

Contact Info

Product

Resources

About