Classification of Benign and Malignant Colorectal Polyps using Pit Pattern Classification

Tanwar, Sushama; Goel, Pallavi; Johri, Prashant; Diván, Mario José

doi:10.2139/ssrn.3558374

Cited by 6 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using pit-pattern classification, a deep learning model was presented in the paper [21] to classify polyps into ,,Benign," ,,Malignant," and ,,Nonmalignant. Here, the model was trained with a private data set and achieved reliability of 84 %.…”

Section: Nice Classificationmentioning

confidence: 99%

Automated classification of polyps using deep learning architectures and few-shot learning

Krenzer

Heil

Fitting

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Colorectal cancer is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is a colonoscopy. However, not all colon polyps have the risk of becoming cancerous. Therefore, polyps are classified using different classification systems. After the classification, further treatment and procedures are based on the classification of the polyp. Nevertheless, classification is not easy. Therefore, we suggest two novel automated classifications system assisting gastroenterologists in classifying polyps based on the NICE and Paris classification. Methods: We build two classification systems. One is classifying polyps based on their shape (Paris). The other classifies polyps based on their texture and surface patterns (NICE). A two-step process for the Paris classification is introduced: First, detecting and cropping the polyp on the image, and secondly, classifying the polyp based on the cropped area with a transformer network. For the NICE classification, we design a few-shot learning algorithm based on the Deep Metric Learning approach. The algorithm creates an embedding space for polyps, which allows classification from a few examples to account for the data scarcity of NICE annotated images in our database. Results: For the Paris classification, we achieve an accuracy of 89.35 %, surpassing all papers in the literature and establishing a new state-of-the-art and baseline accuracy for other publications on a public data set. For the NICE classification, we achieve a competitive accuracy of 81.13 % and demonstrate thereby the viability of the few-shot learning paradigm in polyp classification in data-scarce environments. Additionally, we show different ablations of the algorithms. Finally, we further elaborate on the explainability of the system by showing heat maps of the neural network explaining neural activations. Conclusion: Overall we introduce two polyp classification systems to assist gastroenterologists. We achieve state-of-the-art performance in the Paris classification and demonstrate the viability of the few-shot learning paradigm in the NICE classification, addressing the prevalent data scarcity issues faced in medical machine learning.

show abstract

Section: Nice Classificationmentioning

confidence: 99%

Automated classification of polyps using deep learning architectures and few-shot learning

Krenzer

Heil

Fitting

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Polyps are abnormal tissue growths that can develop in various parts of the body, including the colon and rectum [ 3 ]. Colorectal polyps are common and can be benign (non-cancerous) or malignant (cancerous) [ 4 ]. CRC is a type of cancer that starts in the colon or rectum and is the most commonly diagnosed cancer type in Spain [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

“…3 Colorectal polyps are common and can be benign (non-cancerous) or malignant (cancerous). 4 CRC is a type of cancer that starts in the colon or rectum and is the most commonly diagnosed cancer type in Spain. 5 The primary risk factor for CRC is age, with 90% of all diagnosed patients aged over 50 years.…”

mentioning

confidence: 99%

Unraveling molecular similarities between colorectal polyps and colorectal cancer: a systems biology approach

Radak,

Fallahi

2024

Intest Res

View full text Add to dashboard Cite

Background/Aims: Colorectal cancer (CRC) and colorectal polyps are intimately linked, with polyps acting as precursors to CRC. Understanding the molecular mechanisms governing their development is crucial for advancing diagnosis and treatment. Employing a systems biology approach, we investigated the molecular similarities between polyp and CRC. Methods: We analyzed gene expression profiles, protein-protein interactions, transcription factors, and gene ontology to identify common differentially expressed genes (DEGs) and unravel shared molecular pathways. Results: Our analysis revealed 520 commonly dysregulated genes in polyps and CRC, serving as potential biomarkers and pivotal contributors to disease progression. Gene ontology analysis elucidated distinct biological processes associated with upregulated and downregulated DEGs in both conditions, highlighting common pathways, including signal transduction, cell adhesion, and positive regulation of cell proliferation. Moreover, protein-protein interaction networks shed light on subnetworks involved in rRNA processing, positive regulation of cell proliferation, mRNA splicing, and cell division. Transcription factor analysis identified major regulators and differentially expressed transcription factors in polyp and CRC. Notably, we identified common differentially expressed transcription factors, including ZNF217, NR3C1, KLF5, GATA6, and STAT3, with STAT3 and NR3C1 exhibiting increased expression. Conclusions: This comprehensive analysis enriches our understanding of the molecular mechanisms underlying polyp formation and CRC development, providing potential targets for further investigation and therapeutic intervention. Our findings contribute substantively to crafting personalized strategies for refining the diagnosis and treatment of polyps and CRC.

show abstract

“…Therefore, transfer learning with CNN architectures pre-trained on large datasets as ImageNet 13 is a widely employed strategy. [14][15][16][17][18][19][20] In high-risk medical applications, such as CRP characterization, classification results of such CADx systems should be well-calibrated and reliable to optimally assist clinicians in diagnosis and decision-making. At present, CADx systems are obtaining very promising results towards real-time application, 21 multimodal application 22 and showing feasibility of 'resect and discard' and 'diagnose and leave' strategies 23 by exceeding PIVI thresholds.…”

Section: Introductionmentioning

confidence: 99%

Colorectal polyp classification using confidence-calibrated convolutional neural networks

Kusters

Scheeve

Dehghani

et al. 2022

Medical Imaging 2022: Computer-Aided Diagnosis

View full text Add to dashboard Cite

published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User

show abstract

Classification of Benign and Malignant Colorectal Polyps using Pit Pattern Classification

Cited by 6 publications

References 0 publications

Automated classification of polyps using deep learning architectures and few-shot learning

Automated classification of polyps using deep learning architectures and few-shot learning

Unraveling molecular similarities between colorectal polyps and colorectal cancer: a systems biology approach

Colorectal polyp classification using confidence-calibrated convolutional neural networks

Contact Info

Product

Resources

About