Doctmedico journal logo







TITLE: The review of recent Developments in use of artificial intelligence in cancer detection

Authors: Abbas Jedariforoughi, Farzaneh Karimpour.

Reviewed by: M. Nadi.

ABSTRACT:In recent years there is increasing interest to use artificial intelligence as a cancer detector for better results and precision .But there are some challenges about reliability and professionality that motivate scientists to make different studies to improve the quality of results. In recent years, artificial intelligence (AI) has been found to be useful to physicians in the field of image recognition due to three elements: deep learning (that is, CNN, convolutional neural network), a high-performance computer, and a large amount of digitized data.(14)

KEYWORDS:Artificial intelligence.cancer.Machine Learning. Model base deep learning.Cancer Genome Atlas (TCGA),deep neural networks.electronic health record (EHR).convolutional neural network (CNN). early gastric cancer (EGC).Microsatellite instability (MSI).deficient DNA mismatch repair (dMMR) . colorectal cancer (CRC)

Published in Doctmedico journal. Year:2021 volume:1 issue :2 page 168-171.

DOI : 10.17613/7bp6-z771

PDF   

REFERENCES:(Citation)

  (Bibliography)    




Title :The review of recent Developments in use of artificial intelligence in cancer detection 

Abstract :In recent years there is increasing interest to use artificial intelligence as a cancer detector for better results and precision .But there are some challenges about reliability and professionality that motivate scientists to make different studies to improve the quality of results.

In recent years, artificial intelligence (AI) has been found to be useful to physicians in the field of image recognition due to three elements: deep learning (that is, CNN, convolutional neural network), a high-performance computer, and a large amount of digitized data.(14)

Authors:   Dr Abbas Jedariforoughi MD, Farzaneh Karimpour (computer science)


abbasjedari@yahoo.com

farzaneh.karimpour@yahoo.com

Keywords

Artificial intelligence.cancer.Machine Learning. Model base deep learning.Cancer Genome Atlas (TCGA),deep neural networks.electronic health record(EHR).convolutional neural network (CNN). early gastric cancer (EGC).Microsatellite instability (MSI).deficient DNA mismatch repair (dMMR) .colorectal cancer (CRC) 

Introduction :It is generally accepted that modern AI as a concept first arose at a meeting in Dartmouth College, Hanover, in 1956 which simply challenged: ‘Every aspect of learning or any other feature of intelligence can be so precisely described that a machine can be made to simulate it.(12)

Artificial Intelligence and Machine Learning explores the complexities of this technology, including its role in risk assessment, and understanding of human biology and disease continuum. The emergence of model-based deep learning is considered, as well as how AI has the potential to transform the practice of medicine.(1)

AI will be used to interpret radiographs, ultrasounds, CT, and MRI, either as an adjunct to the clinician's interpretation or as the standalone reading.88 Health care organizations will use AI systems to extract and analyze electronic health record (EHR) data to better identifying risikabel patient and medication errors.(1)

Some study methods used for cancer detection are Automated and computer-aided detection system (CAD) with artificial intelligence and these methods are good to process a large datasets to provide accurate and efficient results in the detection of cancer. However, these processing system have to face many challenges to implement on large scale including image acquisition, pre-processing, segmentation, and data management and classification strategies to be compatible with AI.(15)

Microsatellite instability (MSI) is a molecular marker of deficient DNA mismatch repair (dMMR) that is found in approximately 15% of colorectal cancer (CRC) patients.Machine learning can predict MSI/dMMR with high accuracy in high quality, curated datasets. Accuracy can be significantly decreased when applied to cohorts with different ethnic and/or clinical characteristics, or different tissue preparation protocols. Research is ongoing to determine the optimal machine learning methods for predicting MSI, which will need to be compared to current clinical practices, including next-generation sequencing. Predicting response to immunotherapy remains an unmet need.(17)

Discussion :Advances in artificial intelligence (AI) are driving a revolution across science, enabling exciting new results across chemistry, biology and medicine. Common to these diverse successes are a specific approach to building AI systems, namely, machine learning (ML). (1)

Machine learning refers to the study of algorithms that learn their behavior from data.(1)

The study of deep neural networks is commonly referred to as deep learning.(1)

The goal of cancer screening programs is to enable earlier cancer diagnosis while minimizing screening harms. To achieve this goal, all screening programs rely on cancer risk models, which predict who is likely to develop cancer at a future point in time.(1)

basic research has 2 main dimensions. One is accumulating basic knowledge at the level of molecules, cells, and organisms. Another is basic research at the population level, focusing on risk factors, disease states, progression of disease, and impact of therapies.Artificial intelligence methods make contributions to both of these dimensions. (1)

AI based classification of breast tumor from optically transilluminated data will provide substantial improvement of efficiency of the AI system. Also the proposed system can be utilized along with ultrasonography as a hybrid imaging modality.(7)

Studies detect lung cancer using deep learning methods and determine the contribution of deep learning to the classification of lung carcinoma using a convolutional neural network (CNN).(8)

AI can assist gastroenterologists in imaging-based testing and prediction of clinical diagnosis, for examples, detecting polyps during colonoscopy, identifying small bowel lesions using capsule endoscopy images, and predicting liver diseases based on clinical parameters.(9)

Deep machine learning and AI hold great potential to accurately assess tumor microenvironment models employing vast data management techniques. Despite the significant potential AI holds, there is still much debate surrounding the appropriate and ethical curation of medical data from picture archiving and communication systems.(10)

the artificial intelligence (AI) system allowed for fast and sensitive EGC detection, even for small EGC.(13)

Lung cancer screening (LCS) with low-dose computed tomography (LDCT) helps early lung cancer detection, commonly presenting as small pulmonary nodules. Artificial intelligence (AI)-based vessel suppression (AI-VS) and automatic detection (AI-AD) algorithm can improve detection of subsolid nodules (SSNs) on LDCT.(19)

Conclusion :The Cancer Genome Atlas (TCGA), provided large data sets of genetic and molecular profiles of cancer samples, associated with bioinformatics analyses.Machine learning has opened new doors to the engineering of biomolecules, especially for diagnostic and therapeutic purposes.(1)

AI prototype rapidly and accurately identifies significant risk factors for cardiopulmonary disease on standard screening low-dose chest CT. This information can be used to improve diagnostic ability, facilitate intervention, improve morbidity and mortality, and decrease healthcare costs. (3)

The use of AI was shown to achieve a high accuracy in the detection of early esophageal cancer.(4)

While the era of AI and computer augmented decision-making in medicine is still very much in its infancy, it likely portends a significant revolution in improving the standard of healthcare delivered worldwide, and it is developing rapidly.(12)

References:

  1. Artificial Intelligence and Early Detection of Pancreatic Cancer. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8041569/

  2. Artificial intelligence is a promising prospect for the detection of prostate cancer extracapsular extension with mpMRI: a two-center comparative study

https://link.springer.com/article/10.1007/s00259-021-05381-5

  1. Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening: accuracy and prognostic value https://link.springer.com/article/10.1186/s12916-021-01928-3

  2. Accuracy of artificial intelligence–assisted detection of esophageal cancer and neoplasms on endoscopic images: a systematic review and meta‐analysis

https://onlinelibrary.wiley.com/doi/abs/10.1111/1751-2980.12992?casa_token=xsGnv7V9XVAAAAAA:ywKwHWv6eJpt28sxF9UdBlacHzAjNCt2fM6B1ntQfHwFUyrCLrRVJ8EyATLMuraC5KlMkownumlO_N4

  1. Artificial Intelligence–based Detection of FGFR3 Mutational Status Directly from Routine Histology in Bladder Cancer: A Possible Preselection for Molecular Testing? https://www.sciencedirect.com/science/article/pii/S2405456921001139

  2. Artificial intelligence‐based detection of lymph node metastases by PET/CT predicts prostate cancer‐specific survival https://onlinelibrary.wiley.com/doi/full/10.1111/cpf.12666

  3. Abstract PO-083: Artificial intelligence based detection of breast cancer from transilluminated optical data https://clincancerres.aacrjournals.org/content/27/5_Supplement/PO-083.abstract

  4. Detection Of Lung Cancer On Computed Tomography Using Artificial Intelligence Applications Developed By Deep Learning Methods And The Contribution Of Deep Learning To The …  https://europepmc.org/article/med/33563200

  5. Artificial intelligence for pancreatic cancer detection: Recent development and future direction.  https://www.wjgnet.com/2644-3236/full/v2/i2/56.htm

  6. Tumor microenvironment and the role of artificial intelligence in breast cancer detection and prognosis. https://www.sciencedirect.com/science/article/pii/S0002944021000511

  7. An independent assessment of an artificial intelligence system for prostate cancer detection shows strong diagnostic accuracy https://www.nature.com/articles/s41379-021-00794-x

  8. Intraprocedural Artificial Intelligence for Colorectal Cancer Detection and Characterisation in Endoscopy and Laparoscopy https://journals.sagepub.com/doi/full/10.1177/1553350621997761

  9. How can endoscopists adapt and collaborate with artificial intelligence for early gastric cancer detection?  https://onlinelibrary.wiley.com/doi/full/10.1111/den.13751

  10. Artificial intelligence for cancer detection of the upper gastrointestinal tract. https://onlinelibrary.wiley.com/doi/full/10.1111/den.13897

  11. Artificial Intelligence Techniques for Prostate Cancer Detection through Dual-Channel Tissue Feature Engineering. https://www.mdpi.com/2072-6694/13/7/1524

  12. Artificial intelligence techniques for cancer detection in medical image processing: A review https://www.sciencedirect.com/science/article/pii/S2214785321031618

  13. Artificial Intelligence for Histology-Based Detection of Microsatellite Instability and Prediction of Response to Immunotherapy in Colorectal Cancer. https://www.mdpi.com/2072-6694/13/3/391

  14. Artificial Intelligence Based Algorithms for Prostate Cancer Classification and Detection on Magnetic Resonance Imaging: A Narrative Review. https://www.mdpi.com/2075-4418/11/6/959

  15. Artificial intelligence-based vessel suppression for detection of sub-solid nodules in lung cancer screening computed tomography. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7930659/ 

20.Genomics Data Commons (GDC) data portal (https://portal.gdc.cancer.gov)