Deep transfer learning based model for colorectal cancer histopathology segmentation: A comparative study of deep pre-trained models

2022 ◽  
Vol 159 ◽  
pp. 104669
Author(s):  
Sara Hosseinzadeh Kassani ◽  
Peyman Hosseinzadeh Kassani ◽  
Michal J. Wesolowski ◽  
Kevin A. Schneider ◽  
Ralph Deters
2007 ◽  
Vol 23 (6) ◽  
pp. 477
Author(s):  
Sang Chul Yun ◽  
Hyung Chul Kim ◽  
Chong Woo Chu ◽  
Eung Jin Shin ◽  
Moo Jun Baek ◽  
...  

2017 ◽  
Vol 63 (3) ◽  
pp. 470-474
Author(s):  
Rustem Topuzov ◽  
Georgiy Manikhas ◽  
Eskender Topuzov ◽  
Mikhail Khanevich ◽  
Magomed Abdulaev ◽  
...  

There are presented results of surgical treatment of 347 patients with colorectal cancer. Based on the retrospective analysis a comparative study of results of surgical treatment for colorectal cancer using laparoscopic technologies and “open” access was carried out. Predictive factors that correlate with the risk of postoperative complications with laparoscopic and “open” access at the surgical stage of treatment for colorectal cancer were determined.


Author(s):  
Elene Firmeza Ohata ◽  
João Victor Souza das Chagas ◽  
Gabriel Maia Bezerra ◽  
Mohammad Mehedi Hassan ◽  
Victor Hugo Costa de Albuquerque ◽  
...  

Author(s):  
Parham M. Kebria ◽  
Abbas Khosravi ◽  
Ibrahim Hossain ◽  
Navid Mohajer ◽  
HM Dipu Kabir ◽  
...  

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Young Jae Kim ◽  
Jang Pyo Bae ◽  
Jun-Won Chung ◽  
Dong Kyun Park ◽  
Kwang Gi Kim ◽  
...  

AbstractWhile colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.


Author(s):  
Donato Impedovo ◽  
Vincenzo Dentamaro ◽  
Giacomo Abbattista ◽  
Vincenzo Gattulli ◽  
Giuseppe Pirlo

QJM ◽  
2021 ◽  
Vol 114 (Supplement_1) ◽  
Author(s):  
Tarek Hussein Kamel ◽  
Amr Lotfy Farag ◽  
Dr/Sherif Hassanin Ahmed ◽  
Chresteen Talaat Samy Hanna

Abstract Background Colorectal cancer (CRC) is one of the leading causes of mortality and morbidity in the world. It is the third most common malignancy after lung & breast and the fourth leading cause of cancer-related deaths worldwide, accounting for approximately 1,400,000 new cases and about 700,000 deaths worldwide. Objectives The aim of this retrospective study is to compare the epidemiology, clinicopathologic features, different treatment modalities and outcomes regarding disease free survival (DFS), progression free survival (PFS) & overall survival (OS) of colorectal cancer disease between cases presented to Ain shams university hospital & to Luxor international hospital in 3 consecutive years. Patients and Methods The study is retrospective comparative study. Clinical oncology department in Ain Shams University Hospital and Luxor International Hospital. The data Collected from January 2013 to December 2015. This study analyzed hospital records of patients who diagnosed with colorectal cancer (CRC) and allocated into two groups: Group A: CRC patients presented to Ain-Shams University Hospital from January 2013 to December 2015, group B: CRC patients presented to Luxor International Hospital from January 2013 to December 2015. Results There was no statistically significant difference regarding age parameter in LIH when compared to ASU, but the study was consistent with higher incidence in patients who were aged more than forty- accounted about 70.5% in all CRC cases. Cases less than 40 years old, in group A were 35.2%, while in Group B were 23.5%. Even there was no statistically significant difference but it may be attributable to more westernization in Lower Egypt. Other explanation may be due to decreased low socioeconomic status and different lifestyle factors in more developing region what increase risk of colorectal cancer. Among our cases, there is no statistically significant difference regarding gender between the two hospitals. Both sexes almost were affected equally, females appeared to be at a slightly higher risk of developing CRC cancer with current prevalence 1.3:1 in ASU group, and 1.1:1 in LIH group. Conclusion The need to increase awareness about CRC in Egypt especially upper Egypt, is recommended. An awareness campaign should be performed to promote detection of CRC at its earliest and most curable stage by recognizing early symptoms and enabling early referrals for colonoscopy. Those at higher risk should be offered more intensive surveillance. Similarity of the data from different centers suggests that this is the picture of colorectal cancer typical of Egypt.


Sign in / Sign up

Export Citation Format

Share Document