The diagnosis of Helicobacter Pylori with the improved EfficientNet-B0 architecture

Demet Alıcı Karaca; Bahriye Baştürk Akay; Dervis Karaboga; Alper Baştürk; Özkan Ufuk Nalbantoğlu

Makale detayları

The diagnosis of Helicobacter Pylori with the improved EfficientNet-B0 architecture

Yazarlar:

Demet Alıcı Karaca | Bahriye Baştürk Akay | Dervis Karaboga | Alper Baştürk | Özkan Ufuk Nalbantoğlu

Yayıncı:

Gazi University

Ana Başlıklar:

Biyomedikal Tanı

Dergi:

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.12 Issue 2, pp.729-742

Belge Tipi:

Makale

Yayın Tarihi:

6/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001321581

pISSN:

2147-9526

Anahtar kelimeler:

Özet:

 Gastric cancer is among the leading cancers in cancer-related deaths. Many environmental and genetic factors can cause gastric cancer. However, one of the main risk factors is the helicobacter pylori bacterial virus, which causes gastritis and ulcers in the stomach. Diagnosis of helicobacter pylori is conducted by histopathological evaluation. However, this manual process creates differences of opinion among pathologists from subjective assessment in addition to workload and time loss. Automated systems are needed to speed up the diagnosis process and increase survival time by providing timely treatment to the patient. In recent years, deep learning models, which have proven successful in extracting meaningful results from images, have been used to diagnose the presence of helicobacter pylori from histopathological whole slide images. In this study, an end-to-end deep learning model, EfficientNet-B0, was applied in diagnosing Helicobacter pylori by using DeepHP, which contains gastric biopsy images, a public dataset. Various attention mechanisms introduced in recent years to improve the feature extraction ability of the network Effective Channel Attention, Frequency Channel Attention Network, Gated Channel Transform, Convolutional Block Attention Module, and Simple, Parameter-Free Attention Module were integrated into the deep model and their performances were examined. As a result of the analysis, the Frequency Channel Attention Network integrated into the EfficientNet-B0 architecture reached an accuracy of 0.99835 in diagnosing helicobacter pylori in the histopathological image. The result in the literature on the DeepHP dataset has been surpassed, and the proposed model is promising in diagnosing the disease.

 Gastric cancer is among the leading cancers in cancer-related deaths. Many environmental and genetic factors can cause gastric cancer. However, one of the main risk factors is the helicobacter pylori bacterial virus, which causes gastritis and ulcers in the stomach. Diagnosis of helicobacter pylori is conducted by histopathological evaluation. However, this manual process creates differences of opinion among pathologists from subjective assessment in addition to workload and time loss. Automated systems are needed to speed up the diagnosis process and increase survival time by providing timely treatment to the patient. In recent years, deep learning models, which have proven successful in extracting meaningful results from images, have been used to diagnose the presence of helicobacter pylori from histopathological whole slide images. In this study, an end-to-end deep learning model, EfficientNet-B0, was applied in diagnosing Helicobacter pylori by using DeepHP, which contains gastric biopsy images, a public dataset. Various attention mechanisms introduced in recent years to improve the feature extraction ability of the network Effective Channel Attention, Frequency Channel Attention Network, Gated Channel Transform, Convolutional Block Attention Module, and Simple, Parameter-Free Attention Module were integrated into the deep model and their performances were examined. As a result of the analysis, the Frequency Channel Attention Network integrated into the EfficientNet-B0 architecture reached an accuracy of 0.99835 in diagnosing helicobacter pylori in the histopathological image. The result in the literature on the DeepHP dataset has been surpassed, and the proposed model is promising in diagnosing the disease.

 Gastric cancer is among the leading cancers in cancer-related deaths. Many environmental and genetic factors can cause gastric cancer. However, one of the main risk factors is the helicobacter pylori bacterial virus, which causes gastritis and ulcers in the stomach. Diagnosis of helicobacter pylori is conducted by histopathological evaluation. However, this manual process creates differences of opinion among pathologists from subjective assessment in addition to workload and time loss. Automated systems are needed to speed up the diagnosis process and increase survival time by providing timely treatment to the patient. In recent years, deep learning models, which have proven successful in extracting meaningful results from images, have been used to diagnose the presence of helicobacter pylori from histopathological whole slide images. In this study, an end-to-end deep learning model, EfficientNet-B0, was applied in diagnosing Helicobacter pylori by using DeepHP, which contains gastric biopsy images, a public dataset. Various attention mechanisms introduced in recent years to improve the feature extraction ability of the network Effective Channel Attention, Frequency Channel Attention Network, Gated Channel Transform, Convolutional Block Attention Module, and Simple, Parameter-Free Attention Module were integrated into the deep model and their performances were examined. As a result of the analysis, the Frequency Channel Attention Network integrated into the EfficientNet-B0 architecture reached an accuracy of 0.99835 in diagnosing helicobacter pylori in the histopathological image. The result in the literature on the DeepHP dataset has been surpassed, and the proposed model is promising in diagnosing the disease.

 Kansere bağlı ölümlerde önde gelen türlerden olan mide kanserine çevresel ve genetik birçok faktör sebebiyet verebilir. Başlıca risk faktörlerinden birisi ise midede gastrit ve ülsere neden olan helikobakter pilori bakteri virüsüdür. Bu virüsün tespit edilebilmesi için histopatolojik değerlendirme yapılmaktadır. Manuel yapılan bu işlem iş yükü, zaman kaybı ve subjektif değerlendirmeden kaynaklı patologlar arası görüş ayrılıklarına sebebiyet vermektedir. Tanı sürecini hızlandırmak ve hastaya zamanında tedavi uygulayarak yaşam süresini uzatmak amacıyla otomatik sistemlere ihtiyaç duyulmaktadır. Bu çalışmada son yıllarda başarımı artarak devam eden derin öğrenme mimarisi histopatolojik tam slayt görüntüden helikobakter pilorinin varlığını teşhis etmek için kullanılmaktadır. Mide biyopsi görüntülerini içeren halka açık DeepHP veri seti kullanılarak Helikobakter pilorinin tanısında uçtan-uca bir derin öğrenme modeli olanEfficientNet-B0 uygulanmıştır. Ayrıca, ağın özellik çıkarma yeteneğini geliştirmek amacıyla son zamanlarda literatüre sunulan çeşitli dikkat mekanizmaları Etkili Kanal Dikkat, Frekans Kanal Dikkati Ağı, Kapılı Kanal Dönüşümü, Evrişimsel Blok Dikkat Modülü ve Basit, Parametresiz Dikkat Modülü derin modele entegre edilerek model başarımı üzerindeki etkileri incelenmiştir. Yapılan analizler sonucunda, Frekans Kanal Dikkat Ağı entegre edilen EfficientNet-B0 mimarisinin, histopatolojik görüntülerden helikobakter pilorinin tanısında 0.99835 doğruluğa ulaştığı görülmüştür. Buna göre, önerilen model literatürde yer alan modellerin DeepHP veri seti üzerinde ürettiği sonuçlardan çok daha üstün bir sonuç üretmiştir ve hastalığın tanısında umut vaat edicidir.

Makale detayları

The diagnosis of Helicobacter Pylori with the improved EfficientNet-B0 architecture

Yazarlar:

Demet Alıcı Karaca | Bahriye Baştürk Akay | Dervis Karaboga | Alper Baştürk | Özkan Ufuk Nalbantoğlu

Yayıncı:

Gazi University

Ana Başlıklar:

Biyomedikal Tanı

Dergi:

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.12 Issue 2, pp.729-742

Belge Tipi:

Makale

Yayın Tarihi:

6/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001321581

pISSN:

2147-9526

Helicobacter pylori

deep learning

attention mechanism

histopathologyHelikobakter pilori

derin öğrenme

dikkat mekanizmaları

histopatoloji

Sayı

Makale detayları

Yazarlar: Demet Alıcı Karaca | Bahriye Baştürk Akay | Dervis Karaboga | Alper Baştürk | Özkan Ufuk Nalbantoğlu

Yayıncı: Gazi University

Ana Başlıklar: Biyomedikal Tanı

Dergi: Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.12 Issue 2, pp.729-742

Belge Tipi: Makale

Yayın Tarihi: 6/2024

Belge Dili: Türkçe

Document ID (Org No.): 2001321581

pISSN: 2147-9526

Sayı

Yazarlar:

Demet Alıcı Karaca | Bahriye Baştürk Akay | Dervis Karaboga | Alper Baştürk | Özkan Ufuk Nalbantoğlu

Yayıncı:

Gazi University

Ana Başlıklar:

Biyomedikal Tanı

Dergi:

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji Vol.12 Issue 2, pp.729-742

Belge Tipi:

Makale

Yayın Tarihi:

6/2024

Belge Dili:

Türkçe

Document ID (Org No.):

2001321581

pISSN:

2147-9526