1
|
Tahir AM, Guo L, Ward RK, Yu X, Rideout A, Hore M, Wang ZJ. Explainable machine learning for assessing upper respiratory tract of racehorses from endoscopy videos. Comput Biol Med 2024; 181:109030. [PMID: 39173488 DOI: 10.1016/j.compbiomed.2024.109030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2023] [Revised: 06/20/2024] [Accepted: 08/13/2024] [Indexed: 08/24/2024]
Abstract
Laryngeal hemiplegia (LH) is a major upper respiratory tract (URT) complication in racehorses. Endoscopy imaging of horse throat is a gold standard for URT assessment. However, current manual assessment faces several challenges, stemming from the poor quality of endoscopy videos and subjectivity of manual grading. To overcome such limitations, we propose an explainable machine learning (ML)-based solution for efficient URT assessment. Specifically, a cascaded YOLOv8 architecture is utilized to segment the key semantic regions and landmarks per frame. Several spatiotemporal features are then extracted from key landmarks points and fed to a decision tree (DT) model to classify LH as Grade 1,2,3 or 4 denoting absence of LH, mild, moderate, and severe LH, respectively. The proposed method, validated through 5-fold cross-validation on 107 videos, showed promising performance in classifying different LH grades with 100%, 91.18%, 94.74% and 100% sensitivity values for Grade 1 to 4, respectively. Further validation on an external dataset of 72 cases confirmed its generalization capability with 90%, 80.95%, 100%, and 100% sensitivity values for Grade 1 to 4, respectively. We introduced several explainability related assessment functions, including: (i) visualization of YOLOv8 output to detect landmark estimation errors which can affect the final classification, (ii) time-series visualization to assess video quality, and (iii) backtracking of the DT output to identify borderline cases. We incorporated domain knowledge (e.g., veterinarian diagnostic procedures) into the proposed ML framework. This provides an assistive tool with clinical-relevance and explainability that can ease and speed up the URT assessment by veterinarians.
Collapse
Affiliation(s)
- Anas Mohammed Tahir
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.
| | - Li Guo
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.
| | - Rabab K Ward
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.
| | - Xinhui Yu
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.
| | - Andrew Rideout
- Point To Point Research & Development, Vancouver, BC, Canada.
| | - Michael Hore
- Hagyard Equine Medical Institute, Lexington, KY, USA.
| | - Z Jane Wang
- Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.
| |
Collapse
|
2
|
Xu Y, Wang J, Li C, Su Y, Peng H, Guo L, Lin S, Li J, Wu D. Advancing precise diagnosis of nasopharyngeal carcinoma through endoscopy-based radiomics analysis. iScience 2024; 27:110590. [PMID: 39252978 PMCID: PMC11381885 DOI: 10.1016/j.isci.2024.110590] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/30/2024] [Revised: 05/25/2024] [Accepted: 07/23/2024] [Indexed: 09/11/2024] Open
Abstract
Nasopharyngeal carcinoma (NPC) has high metastatic potential and is hard to detect early. This study aims to develop a deep learning model for NPC diagnosis using optical imagery. From April 2008 to May 2021, we analyzed 12,087 nasopharyngeal endoscopic images and 309 videos from 1,108 patients. The pretrained model was fine-tuned with stochastic gradient descent on the final layers. Data augmentation was applied during training. Videos were converted to images for malignancy scoring. Performance metrics like AUC, accuracy, and sensitivity were calculated based on the malignancy score. The deep learning model demonstrated high performance in identifying NPC, with AUC values of 0.981 (95% confidence of interval [CI] 0.965-0.996) for the Fujian Cancer Hospital dataset and 0.937 (0.905-0.970) for the Jiangxi Cancer Hospital dataset. The proposed model effectively diagnoses NPC with high accuracy, sensitivity, and specificity across multiple datasets. It shows promise for early NPC detection, especially in identifying latent lesions.
Collapse
Affiliation(s)
- Yun Xu
- Department of Radiation Oncology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China
- Fujian Key Laboratory of Translational Cancer Medicine, Fuzhou, Fujian, China
| | - Jiesong Wang
- Department of Lymphoma & Head and Neck Oncology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China
| | - Chenxin Li
- Department of Electrical Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China
| | - Yong Su
- Department of Radiation Oncology, Jiangxi Cancer Hospital, Jiangxi, China
- National Health Commission (NHC) Key Laboratory of Personalized Diagnosis and Treatment of Nasopharyngeal Carcinoma (Jiangxi Cancer Hospital of Nanchang University), Nanchang, China
| | - Hewei Peng
- Department of Epidemiology and Health Statistics, Fujian Provincial Key Laboratory of Environment Factors and Cancer, School of Public Health, Fujian Medical University, Fuzhou, China
| | - Lanyan Guo
- School of Medical Imaging, Fujian Medical University, Fuzhou, China
| | - Shaojun Lin
- Department of Radiation Oncology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China
- Fujian Key Laboratory of Translational Cancer Medicine, Fuzhou, Fujian, China
| | - Jingao Li
- Department of Radiation Oncology, Jiangxi Cancer Hospital, Jiangxi, China
- National Health Commission (NHC) Key Laboratory of Personalized Diagnosis and Treatment of Nasopharyngeal Carcinoma (Jiangxi Cancer Hospital of Nanchang University), Nanchang, China
| | - Dan Wu
- Tianjin Key Laboratory of Human Development and Reproductive Regulation, Tianjin Central Hospital of Gynecology Obstetrics and Nankai University Affiliated Hospital of Obstetrics and Gynecology, Tianjin, China
- Tianjin Cancer Institute, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Tianjin Medical University Cancer Institute and Hospital, Tianjin Medical University, Tianjin, China
| |
Collapse
|
3
|
Ganeshan V, Bidwell J, Gyawali D, Nguyen TS, Morse J, Smith MP, Barton BM, McCoul ED. Enhancing nasal endoscopy: Classification, detection, and segmentation of anatomic landmarks using a convolutional neural network. Int Forum Allergy Rhinol 2024; 14:1521-1524. [PMID: 38853655 DOI: 10.1002/alr.23384] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2024] [Revised: 05/14/2024] [Accepted: 05/23/2024] [Indexed: 06/11/2024]
Abstract
KEY POINTS A convolutional neural network (CNN)-based model can accurately localize and segment turbinates in images obtained during nasal endoscopy (NE). This model represents a starting point for algorithms that comprehensively interpret NE findings.
Collapse
Affiliation(s)
- Vinayak Ganeshan
- Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA
| | - Jonathan Bidwell
- Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA
| | - Dipesh Gyawali
- Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA
| | - Thinh S Nguyen
- Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA
| | - Jonathan Morse
- Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA
| | - Madeline P Smith
- Ochsner Clinical School, University of Queensland, New Orleans, Louisiana, USA
- Department of Otolaryngology, Tulane University School of Medicine, New Orleans, Louisiana, USA
| | - Blair M Barton
- Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA
- Ochsner Clinical School, University of Queensland, New Orleans, Louisiana, USA
- Department of Otolaryngology, Tulane University School of Medicine, New Orleans, Louisiana, USA
| | - Edward D McCoul
- Department of Otorhinolaryngology, Ochsner Health, New Orleans, Louisiana, USA
- Ochsner Clinical School, University of Queensland, New Orleans, Louisiana, USA
- Department of Otolaryngology, Tulane University School of Medicine, New Orleans, Louisiana, USA
| |
Collapse
|
4
|
Zhang J, Weng Y, Liu Y, Wang N, Feng S, Qiu S, Lin D. Molecular separation-assisted label-free SERS combined with machine learning for nasopharyngeal cancer screening and radiotherapy resistance prediction. JOURNAL OF PHOTOCHEMISTRY AND PHOTOBIOLOGY. B, BIOLOGY 2024; 257:112968. [PMID: 38955080 DOI: 10.1016/j.jphotobiol.2024.112968] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/24/2023] [Revised: 04/30/2024] [Accepted: 06/25/2024] [Indexed: 07/04/2024]
Abstract
Nasopharyngeal cancer (NPC) is a malignant tumor with high prevalence in Southeast Asia and highly invasive and metastatic characteristics. Radiotherapy is the primary strategy for NPC treatment, however there is still lack of effect method for predicting the radioresistance that is the main reason for treatment failure. Herein, the molecular profiles of patient plasma from NPC with radiotherapy sensitivity and resistance groups as well as healthy group, respectively, were explored by label-free surface enhanced Raman spectroscopy (SERS) based on surface plasmon resonance for the first time. Especially, the components with different molecular weight sizes were analyzed via the separation process, helping to avoid the possible missing of diagnostic information due to the competitive adsorption. Following that, robust machine learning algorithm based on principal component analysis and linear discriminant analysis (PCA-LDA) was employed to extract the feature of blood-SERS data and establish an effective predictive model with the accuracy of 96.7% for identifying the radiotherapy resistance subjects from sensitivity ones, and 100% for identifying the NPC subjects from healthy ones. This work demonstrates the potential of molecular separation-assisted label-free SERS combined with machine learning for NPC screening and treatment strategy guidance in clinical scenario.
Collapse
Affiliation(s)
- Jun Zhang
- Key Laboratory of OptoElectronic Science and Technology for Medicine, Ministry of Education, Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou 350117, PR China
| | - Youliang Weng
- Department of Radiation Oncology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fujian Branch of Fudan University Shanghai Cancer Center, Fuzhou 350014, PR China
| | - Yi Liu
- Key Laboratory of OptoElectronic Science and Technology for Medicine, Ministry of Education, Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou 350117, PR China
| | - Nan Wang
- Key Laboratory of OptoElectronic Science and Technology for Medicine, Ministry of Education, Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou 350117, PR China
| | - Shangyuan Feng
- Key Laboratory of OptoElectronic Science and Technology for Medicine, Ministry of Education, Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou 350117, PR China
| | - Sufang Qiu
- Department of Radiation Oncology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fujian Branch of Fudan University Shanghai Cancer Center, Fuzhou 350014, PR China.
| | - Duo Lin
- Key Laboratory of OptoElectronic Science and Technology for Medicine, Ministry of Education, Fujian Provincial Key Laboratory for Photonics Technology, Fujian Normal University, Fuzhou 350117, PR China.
| |
Collapse
|
5
|
Yoshizaki T, Kondo S, Dochi H, Kobayashi E, Mizokami H, Komura S, Endo K. Recent Advances in Assessing the Clinical Implications of Epstein-Barr Virus Infection and Their Application to the Diagnosis and Treatment of Nasopharyngeal Carcinoma. Microorganisms 2023; 12:14. [PMID: 38276183 PMCID: PMC10820804 DOI: 10.3390/microorganisms12010014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Revised: 12/12/2023] [Accepted: 12/16/2023] [Indexed: 01/27/2024] Open
Abstract
Reports about the oncogenic mechanisms underlying nasopharyngeal carcinoma (NPC) have been accumulating since the discovery of Epstein-Barr virus (EBV) in NPC cells. EBV is the primary causative agent of NPC. EBV-host and tumor-immune system interactions underlie the unique representative pathology of NPC, which is an undifferentiated cancer cell with extensive lymphocyte infiltration. Recent advances in the understanding of immune evasion and checkpoints have changed the treatment of NPC in clinical settings. The main EBV genes involved in NPC are LMP1, which is the primary EBV oncogene, and BZLF1, which induces the lytic phase of EBV. These two multifunctional genes affect host cell behavior, including the tumor-immune microenvironment and EBV behavior. Latent infections, elevated concentrations of the anti-EBV antibody and plasma EBV DNA have been used as biomarkers of EBV-associated NPC. The massive infiltration of lymphocytes in the stroma suggests the immunogenic characteristics of NPC as a virus-infected tumor and, at the same time, also indicates the presence of a sophisticated immunosuppressive system within NPC tumors. In fact, immune checkpoint inhibitors have shown promise in improving the prognosis of NPC patients with recurrent and metastatic disease. However, patients with advanced NPC still require invasive treatments. Therefore, there is a pressing need to develop an effective screening system for early-stage detection of NPC in patients. Various modalities, such as nasopharyngeal cytology, cell-free DNA methylation, and deep learning-assisted nasopharyngeal endoscopy for screening and diagnosis, have been introduced. Each modality has its advantages and disadvantages. A reciprocal combination of these modalities will improve screening and early diagnosis of NPC.
Collapse
|