دانلود مقاله مرور استفاده از هوش مصنوعی در تشخیص زودهنگام سرطان دهانی
خلاصه
مقدمه
روش
نتایج
بحث
نتیجه
اعلام منافع متضاد
منابع مالی
مشارکت های نویسنده
منابع
Abstract
Introduction
Method
Results
Discussion
Conclusion
Declaration of conflicting interests
Funding
Author contributions
References
چکیده
وقوع جهانی سرطان دهان در سال های اخیر افزایش یافته است. سرطان دهان که در مراحل پیشرفته تشخیص داده می شود منجر به عوارض و مرگ و میر می شود. استفاده از فناوری ممکن است برای تشخیص و تشخیص زودهنگام مفید باشد و در نتیجه به پزشک در مدیریت بهتر بیمار کمک کند. ظهور هوش مصنوعی (AI) پتانسیل بهبود غربالگری سرطان دهان را دارد. هوش مصنوعی می تواند به طور دقیق مجموعه داده های عظیمی را از روش های مختلف تصویربرداری تجزیه و تحلیل کند و در زمینه سرطان شناسی کمک کند. این بررسی بر کاربردهای هوش مصنوعی در تشخیص زودهنگام و پیشگیری از سرطان دهان متمرکز بود. جستجوی ادبیات در پایگاه‌های اطلاعاتی PubMed و Scopus با استفاده از اصطلاحات جستجوی "سرطان دهان" و "هوش مصنوعی" انجام شد. اطلاعات بیشتر در مورد موضوع با بررسی دقیق فهرست منابع مقالات منتخب جمع آوری شد. بر اساس اطلاعات به‌دست‌آمده، این مقاله کاربردها و مزایای هوش مصنوعی در غربالگری سرطان دهان، تشخیص زودهنگام، پیش‌بینی بیماری، برنامه‌ریزی درمان و پیش‌آگهی را مورد بررسی و بحث قرار می‌دهد. محدودیت ها و دامنه آینده هوش مصنوعی در تحقیقات سرطان دهان نیز برجسته شده است.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
The global occurrence of oral cancer has increased in recent years. Oral cancer diagnosed in the advanced stages results in morbidity and mortality. The use of technology may be beneficial for early detection and diagnosis, and thus help the clinician with better patient management. The advent of artificial intelligence (AI) has the potential to improve oral cancer screening. AI can precisely analyze an enormous dataset from various imaging modalities and provide assistance in the field of oncology. This review focused on the applications of artificial intelligence in the early diagnosis and prevention of oral cancer. A literature search was conducted in the PubMed and Scopus databases using the search terminology “oral cancer” and “artificial intelligence”. Further information regarding the topic was collected by scrutinizing the reference lists of selected articles. Based on the information obtained, this article reviews and discusses the applications and advantages of AI in oral cancer screening, early diagnosis, disease prediction, treatment planning, and prognosis. Limitations and the future scope of AI in oral cancer research are also highlighted.
Introduction
The global occurrence of Oral cancer (OC) has increased in recent years, with Oral squamous cell carcinomas (OSCCs) counting for more than 90% of these cancers.[1] OSCCs are also the sixth most common malignancy in the world. In 2012, The World Health Organization reported 529 000 new cases of OC and 300 000 deaths due to OC each year.[2] Oral cancer diagnosed in the advanced stage results in morbidity and mortality. A crucial factor in providing successful treatment is the early detection of cancerous lesions. Inaccessible lesions and the late detection of cancers are associated with low survival, increased symptoms, and a higher treatment cost.[3] Early diagnosis can increase the survival rate to 75–90%.1,4
Early detection includes the diagnosis of oral potentially malignant disorders and regular follow-ups. Oral potentially malignant disorders (OPMDs) have been defined as “any oral mucosal abnormality that is associated with a statistically increased risk of developing oral cancer.”[5] OPMDs include oral leukoplakia, proliferative verrucous leukoplakia, erythroplakia, oral lichen planus, oral submucous fibrosis, palatal lesions in reverse smokers, oral lupus erythematosus, actinic keratosis, and dyskeratosis congenita. Newly included lesions in the recent classification are oral lichenoid lesion and oral chronic graft-versus-host disease.[5]
Conclusion
In recent years, the use of AI for the diagnosis and prognosis of diseases has evolved. Previous studies have proved that ML produces accurate results for OC detection. It assists clinicians in diagnostic processes and minimizes inadvertent errors. However, previous studies based on deep learning (neural network) provided more accuracy with the early detection of OC as compared to machine learning. AI presents the opportunity to develop new techniques combined with traditional approaches to improve the accuracy of detection of OC and OPMDs, as well as to predict the course of the precancerous/cancerous lesions from retrospective data. Future research could consider the innovation of data fusion algorithms combining various modalities, such as clinical, radiological, histological, and molecular assessments, to support the early diagnosis and outcome estimation of the disease.