1
|
Albalawi E, Thakur A, Ramakrishna MT, Bhatia Khan S, SankaraNarayanan S, Almarri B, Hadi TH. Oral squamous cell carcinoma detection using EfficientNet on histopathological images. Front Med (Lausanne) 2024; 10:1349336. [PMID: 38348235 PMCID: PMC10859441 DOI: 10.3389/fmed.2023.1349336] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/04/2023] [Accepted: 12/28/2023] [Indexed: 02/15/2024] Open
Abstract
Introduction Oral Squamous Cell Carcinoma (OSCC) poses a significant challenge in oncology due to the absence of precise diagnostic tools, leading to delays in identifying the condition. Current diagnostic methods for OSCC have limitations in accuracy and efficiency, highlighting the need for more reliable approaches. This study aims to explore the discriminative potential of histopathological images of oral epithelium and OSCC. By utilizing a database containing 1224 images from 230 patients, captured at varying magnifications and publicly available, a customized deep learning model based on EfficientNetB3 was developed. The model's objective was to differentiate between normal epithelium and OSCC tissues by employing advanced techniques such as data augmentation, regularization, and optimization. Methods The research utilized a histopathological imaging database for Oral Cancer analysis, incorporating 1224 images from 230 patients. These images, taken at various magnifications, formed the basis for training a specialized deep learning model built upon the EfficientNetB3 architecture. The model underwent training to distinguish between normal epithelium and OSCC tissues, employing sophisticated methodologies including data augmentation, regularization techniques, and optimization strategies. Results The customized deep learning model achieved significant success, showcasing a remarkable 99% accuracy when tested on the dataset. This high accuracy underscores the model's efficacy in effectively discerning between normal epithelium and OSCC tissues. Furthermore, the model exhibited impressive precision, recall, and F1-score metrics, reinforcing its potential as a robust diagnostic tool for OSCC. Discussion This research demonstrates the promising potential of employing deep learning models to address the diagnostic challenges associated with OSCC. The model's ability to achieve a 99% accuracy rate on the test dataset signifies a considerable leap forward in earlier and more accurate detection of OSCC. Leveraging advanced techniques in machine learning, such as data augmentation and optimization, has shown promising results in improving patient outcomes through timely and precise identification of OSCC.
Collapse
Affiliation(s)
- Eid Albalawi
- Department of Computer Science, College of Computer Science and Information Technology, King Faisal University, Al-Ahsa, Saudi Arabia
| | - Arastu Thakur
- Department of Computer Science and Engineering, Faculty of Engineering and Technology, JAIN (Deemed-to-be University), Bangalore, India
| | - Mahesh Thyluru Ramakrishna
- Department of Computer Science and Engineering, Faculty of Engineering and Technology, JAIN (Deemed-to-be University), Bangalore, India
| | - Surbhi Bhatia Khan
- Department of Data Science, School of Science, Engineering and Environment, University of Salford, Salford, United Kingdom
- Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon
| | - Suresh SankaraNarayanan
- Department of Computer Science, College of Computer Science and Information Technology, King Faisal University, Al-Ahsa, Saudi Arabia
| | - Badar Almarri
- Department of Computer Science, College of Computer Science and Information Technology, King Faisal University, Al-Ahsa, Saudi Arabia
| | - Theyazn Hassn Hadi
- Applied College in Abqaiq, King Faisal University, Al-Ahsa, Saudi Arabia
| |
Collapse
|
2
|
Rutland CS, Cockcroft JM, Lothion-Roy J, Harris AE, Jeyapalan JN, Simpson S, Alibhai A, Bailey C, Ballard-Reisch AC, Rizvanov AA, Dunning MD, de Brot S, Mongan NP. Immunohistochemical Characterisation of GLUT1, MMP3 and NRF2 in Osteosarcoma. Front Vet Sci 2021; 8:704598. [PMID: 34414229 PMCID: PMC8369506 DOI: 10.3389/fvets.2021.704598] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Accepted: 07/08/2021] [Indexed: 12/12/2022] Open
Abstract
Osteosarcoma (OSA) is an aggressive bone malignancy. Unlike many other malignancies, OSA outcomes have not improved in recent decades. One challenge to the development of better diagnostic and therapeutic methods for OSA has been the lack of well characterized experimental model systems. Spontaneous OSA in dogs provides a good model for the disease seen in people and also remains an important veterinary clinical challenge. We recently used RNA sequencing and qRT-PCR to provide a detailed molecular characterization of OSA relative to non-malignant bone in dogs. We identified differential mRNA expression of the solute carrier family 2 member 1 (SLC2A1/GLUT1), matrix metallopeptidase 3 (MMP3) and nuclear factor erythroid 2–related factor 2 (NFE2L2/NRF2) genes in canine OSA tissue in comparison to paired non-tumor tissue. Our present work characterizes protein expression of GLUT1, MMP3 and NRF2 using immunohistochemistry. As these proteins affect key processes such as Wnt activation, heme biosynthesis, glucose transport, understanding their expression and the enriched pathways and gene ontologies enables us to further understand the potential molecular pathways and mechanisms involved in OSA. This study further supports spontaneous OSA in dogs as a model system to inform the development of new methods to diagnose and treat OSA in both dogs and people.
Collapse
Affiliation(s)
- Catrin S Rutland
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom
| | - James M Cockcroft
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom
| | - Jennifer Lothion-Roy
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom.,Faculty of Medicine and Health Science, Biodiscovery Institute, University of Nottingham, Nottingham, United Kingdom
| | - Anna E Harris
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom.,Faculty of Medicine and Health Science, Biodiscovery Institute, University of Nottingham, Nottingham, United Kingdom
| | - Jennie N Jeyapalan
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom.,Faculty of Medicine and Health Science, Biodiscovery Institute, University of Nottingham, Nottingham, United Kingdom
| | - Siobhan Simpson
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom
| | - Aziza Alibhai
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom
| | - Clara Bailey
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom
| | | | - Albert A Rizvanov
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom.,Institute of Fundamental Medicine and Biology, Kazan Federal University, Kazan, Russia
| | - Mark D Dunning
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom.,Willows Veterinary Centre and Referral Service, Solihull, United Kingdom
| | - Simone de Brot
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom.,COMPATH, Institute of Animal Pathology, University of Bern, Bern, Switzerland
| | - Nigel P Mongan
- School of Veterinary Medicine and Science, Faculty of Medicine and Health Sciences, University of Nottingham, Nottingham, United Kingdom.,Faculty of Medicine and Health Science, Biodiscovery Institute, University of Nottingham, Nottingham, United Kingdom.,Department of Pharmacology, Weill Cornell Medicine, New York, NY, United States
| |
Collapse
|
3
|
Chuang WY, Chang SH, Yu WH, Yang CK, Yeh CJ, Ueng SH, Liu YJ, Chen TD, Chen KH, Hsieh YY, Hsia Y, Wang TH, Hsueh C, Kuo CF, Yeh CY. Successful Identification of Nasopharyngeal Carcinoma in Nasopharyngeal Biopsies Using Deep Learning. Cancers (Basel) 2020; 12:cancers12020507. [PMID: 32098314 PMCID: PMC7072217 DOI: 10.3390/cancers12020507] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2020] [Revised: 02/16/2020] [Accepted: 02/19/2020] [Indexed: 12/14/2022] Open
Abstract
Pathologic diagnosis of nasopharyngeal carcinoma (NPC) can be challenging since most cases are nonkeratinizing carcinoma with little differentiation and many admixed lymphocytes. Our aim was to evaluate the possibility to identify NPC in nasopharyngeal biopsies using deep learning. A total of 726 nasopharyngeal biopsies were included. Among them, 100 cases were randomly selected as the testing set, 20 cases as the validation set, and all other 606 cases as the training set. All three datasets had equal numbers of NPC cases and benign cases. Manual annotation was performed. Cropped square image patches of 256 × 256 pixels were used for patch-level training, validation, and testing. The final patch-level algorithm effectively identified NPC patches, with an area under the receiver operator characteristic curve (AUC) of 0.9900. Using gradient-weighted class activation mapping, we demonstrated that the identification of NPC patches was based on morphologic features of tumor cells. At the second stage, whole-slide images were sequentially cropped into patches, inferred with the patch-level algorithm, and reconstructed into images with a smaller size for training, validation, and testing. Finally, the AUC was 0.9848 for slide-level identification of NPC. Our result shows for the first time that deep learning algorithms can identify NPC.
Collapse
Affiliation(s)
- Wen-Yu Chuang
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
- Center for Vascularized Composite Allotransplantation, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan
| | - Shang-Hung Chang
- Center for Big Data Analytics and Statistics, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan;
| | - Wei-Hsiang Yu
- aetherAI, Co., Ltd., No. 3-2, Yuan-Qu Street, Nangang District, Taipei City 115, Taiwan; (W.-H.Y.); (C.-K.Y.)
| | - Cheng-Kun Yang
- aetherAI, Co., Ltd., No. 3-2, Yuan-Qu Street, Nangang District, Taipei City 115, Taiwan; (W.-H.Y.); (C.-K.Y.)
| | - Chi-Ju Yeh
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
| | - Shir-Hwa Ueng
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
- Chang Gung Molecular Medicine Research Center, Chang Gung University, No. 259, Wenhua First Road, Guishan District, Taoyuan City 333, Taiwan
| | - Yu-Jen Liu
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
| | - Tai-Di Chen
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
| | - Kuang-Hua Chen
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
| | - Yi-Yin Hsieh
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
| | - Yi Hsia
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
- Department of Pathology, MacKay Memorial Hospital, No. 92, Section 2, Zhongshan North Road, Zhongshan District, Taipei City 104, Taiwan
| | - Tong-Hong Wang
- Tissue Bank, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan;
| | - Chuen Hsueh
- Department of Pathology, Chang Gung Memorial Hospital and Chang Gung University, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan; (W.-Y.C.); (C.-J.Y.); (S.-H.U.); (Y.-J.L.); (T.-D.C.); (K.-H.C.); (Y.-Y.H.); (Y.H.); (C.H.)
- Chang Gung Molecular Medicine Research Center, Chang Gung University, No. 259, Wenhua First Road, Guishan District, Taoyuan City 333, Taiwan
| | - Chang-Fu Kuo
- Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, No. 5, Fuxing Street, Guishan District, Taoyuan City 333, Taiwan;
| | - Chao-Yuan Yeh
- aetherAI, Co., Ltd., No. 3-2, Yuan-Qu Street, Nangang District, Taipei City 115, Taiwan; (W.-H.Y.); (C.-K.Y.)
- Correspondence: ; Tel.: +886-2-27856892
| |
Collapse
|