1
|
Ren J, Yang G, Song Y, Zhang C, Yuan Y. Machine learning-based MRI radiomics for assessing the level of tumor infiltrating lymphocytes in oral tongue squamous cell carcinoma: a pilot study. BMC Med Imaging 2024; 24:33. [PMID: 38317076 PMCID: PMC10845803 DOI: 10.1186/s12880-024-01210-x] [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: 10/16/2023] [Accepted: 01/22/2024] [Indexed: 02/07/2024] Open
Abstract
BACKGROUND To investigate the value of machine learning (ML)-based magnetic resonance imaging (MRI) radiomics in assessing tumor-infiltrating lymphocyte (TIL) levels in patients with oral tongue squamous cell carcinoma (OTSCC). METHODS The study included 68 patients with pathologically diagnosed OTSCC (30 with high TILs and 38 with low TILs) who underwent pretreatment MRI. Based on the regions of interest encompassing the entire tumor, a total of 750 radiomics features were extracted from T2-weighted (T2WI) and contrast-enhanced T1-weighted (ceT1WI) imaging. To reduce dimensionality, reproducibility analysis by two radiologists and collinearity analysis were performed. The top six features were selected from each sequence alone, as well as their combination, using the minimum-redundancy maximum-relevance algorithm. Random forest, logistic regression, and support vector machine models were used to predict TIL levels in OTSCC, and 10-fold cross-validation was employed to assess the performance of the classifiers. RESULTS Based on the features selected from each sequence alone, the ceT1WI models outperformed the T2WI models, with a maximum area under the curve (AUC) of 0.820 versus 0.754. When combining the two sequences, the optimal features consisted of one T2WI and five ceT1WI features, all of which exhibited significant differences between patients with low and high TILs (all P < 0.05). The logistic regression model constructed using these features demonstrated the best predictive performance, with an AUC of 0.846 and an accuracy of 80.9%. CONCLUSIONS ML-based T2WI and ceT1WI radiomics can serve as valuable tools for determining the level of TILs in patients with OTSCC.
Collapse
Affiliation(s)
- Jiliang Ren
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, No.639 Zhizaoju Road, 200010, Shanghai, China
| | - Gongxin Yang
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, No.639 Zhizaoju Road, 200010, Shanghai, China
| | - Yang Song
- MR Scientific Marketing, Siemens Healthineers Ltd, 200126, Shanghai, China
| | - Chunye Zhang
- Department of Oral Pathology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, No.639 Zhizaoju Road, 200010, Shanghai, China.
| | - Ying Yuan
- Department of Radiology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, No.639 Zhizaoju Road, 200010, Shanghai, China.
| |
Collapse
|
2
|
Mossinelli C, Tagliabue M, Ruju F, Cammarata G, Volpe S, Raimondi S, Zaffaroni M, Isaksson JL, Garibaldi C, Cremonesi M, Corso F, Gaeta A, Emili I, Zorzi S, Alterio D, Marvaso G, Pepa M, De Fiori E, Maffini F, Preda L, Benazzo M, Jereczek-Fossa BA, Ansarin M. The role of radiomics in tongue cancer: A new tool for prognosis prediction. Head Neck 2023; 45:849-861. [PMID: 36779382 DOI: 10.1002/hed.27299] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/01/2022] [Revised: 11/08/2022] [Accepted: 12/27/2022] [Indexed: 02/14/2023] Open
Abstract
BACKGROUND Radiomics represents an emerging field of precision-medicine. Its application in head and neck is still at the beginning. METHODS Retrospective study about magnetic resonance imaging (MRI) based radiomics in oral tongue squamous cell carcinoma (OTSCC) surgically treated (2010-2019; 79 patients). All preoperative MRIs include different sequences (T1, T2, DWI, ADC). Tumor volume was manually segmented and exported to radiomic-software, to perform feature extraction. Statistically significant variables were included in multivariable analysis and related to survival endpoints. Predictive models were elaborated (clinical, radiomic, clinical-radiomic models) and compared using C-index. RESULTS In almost all clinical-radiomic models radiomic-score maintained statistical significance. In all cases C-index was higher in clinical-radiomic models than in clinical ones. ADC provided the best fit to the models (C-index 0.98, 0.86, 0.84 in loco-regional recurrence, cause-specific mortality, overall survival, respectively). CONCLUSION MRI-based radiomics in OTSCC represents a promising noninvasive method of precision medicine, improving prognosis prediction before surgery.
Collapse
Affiliation(s)
- Chiara Mossinelli
- Department of Otorhinolaryngology and Head and Neck Surgery, European Institute of Oncology, IRCCS, Milan, Italy
| | - Marta Tagliabue
- Department of Otorhinolaryngology and Head and Neck Surgery, European Institute of Oncology, IRCCS, Milan, Italy.,Department of Biomedical Sciences, University of Sassari, Sassari, Italy
| | - Francesca Ruju
- Division of Radiology, IEO, European Institute of Oncology, IRCCS, Milan, Italy
| | - Giulio Cammarata
- Department of Experimental Oncology, IEO European Institute of Experimental Oncology IRCCS, Milan, Italy
| | - Stefania Volpe
- Division of Radiation Oncology, European Institute of Oncology, IRCCS, Milan, Italy.,Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - Sara Raimondi
- Department of Experimental Oncology, IEO European Institute of Experimental Oncology IRCCS, Milan, Italy
| | - Mattia Zaffaroni
- Division of Radiation Oncology, European Institute of Oncology, IRCCS, Milan, Italy
| | | | - Cristina Garibaldi
- Unit of Radiation Research, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Marta Cremonesi
- Unit of Radiation Research, IEO European Institute of Oncology, IRCCS, Milan, Italy
| | - Federica Corso
- Department of Experimental Oncology, IEO European Institute of Experimental Oncology IRCCS, Milan, Italy.,Department of Mathematics (DMAT), Politecnico di Milano, Milan, Italy.,Centre for Health Data Science (CHDS), Human Techonopole
| | - Aurora Gaeta
- Department of Experimental Oncology, IEO European Institute of Experimental Oncology IRCCS, Milan, Italy
| | - Ilaria Emili
- Division of Radiology, IEO, European Institute of Oncology, IRCCS, Milan, Italy.,ASST Centro Specialistico Ortopedico Traumatologico G. Pini/C.T.O, Milan, Italy
| | - Stefano Zorzi
- Department of Otorhinolaryngology and Head and Neck Surgery, European Institute of Oncology, IRCCS, Milan, Italy
| | - Daniela Alterio
- Division of Radiation Oncology, European Institute of Oncology, IRCCS, Milan, Italy
| | - Giulia Marvaso
- Division of Radiation Oncology, European Institute of Oncology, IRCCS, Milan, Italy.,Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - Matteo Pepa
- Division of Radiation Oncology, European Institute of Oncology, IRCCS, Milan, Italy
| | - Elvio De Fiori
- Division of Radiology, IEO, European Institute of Oncology, IRCCS, Milan, Italy
| | - Fausto Maffini
- Division of Pathology, IEO, European Institute of Oncology, IRCCS, Milan, Italy
| | - Lorenzo Preda
- Department of Clinical, Surgical, Diagnostic, and Pediatric Sciences, University of Pavia, Pavia, Italy.,Division of Radiology, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
| | - Marco Benazzo
- Department of Clinical, Surgical, Diagnostic, and Pediatric Sciences, University of Pavia, Pavia, Italy.,Department of Otorhinolaryngology, Fondazione IRCCS Policlinico San Matteo, Pavia, Italy
| | - Barbara Alicja Jereczek-Fossa
- Division of Radiation Oncology, European Institute of Oncology, IRCCS, Milan, Italy.,Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy
| | - Mohssen Ansarin
- Department of Otorhinolaryngology and Head and Neck Surgery, European Institute of Oncology, IRCCS, Milan, Italy
| |
Collapse
|
4
|
Fiorillo A, Sorrentino A, Scala A, Abbate V, Dell'aversana Orabona G. Improving performance of the hospitalization process by applying the principles of Lean Thinking. TQM JOURNAL 2021. [DOI: 10.1108/tqm-09-2020-0207] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/13/2023]
Abstract
PurposeThe goal was to improve the quality of the hospitalization process and the management of patients, allowing the reduction of costs and the minimization of the preoperative Length of Hospital Stay (LOS).Design/methodology/approachThe methodology used to improve the quality of the hospitalization process and patient management was Lean Thinking. Therefore, the Lean tools (Value stream map and Ishikawa diagram) were used to identify waste and inefficiencies, improving the process with the implementation of corrective actions. The data was collected through personal observations, patient interviews, brainstorming and from printed medical records of 151 patients undergoing oral cancer surgery in the period from 2006 to 2018.FindingsThe authors identified, through Value Stream Map, waste and inefficiencies during preoperative activities, consequently influencing preoperative LOS, considered the best performance indicator. The main causes were identified through the Ishikawa diagram, allowing reflection on possible solutions. The main corrective action was the introduction of the pre-hospitalization service. A comparative statistical analysis showed the significance of the solutions implemented. The average preoperative LOS decreased from 4.90 to 3.80 days (−22.40%) with a p-value of 0.001.Originality/valueThe methodology allowed to highlight the improvement of the patient hospitalization process with the introduction of the pre-hospitalization service. Therefore, by adopting the culture of continuous improvement, the flow of hospitalization was redrawn. The benefits of the solutions implemented are addressed to the patient in terms of lower LOS and greater service satisfaction and to the hospital for lower patient management costs and improved process quality. This article will be useful for those who need examples on how to apply Lean tools in healthcare.
Collapse
|
5
|
Mahajan A, Ahuja A, Sable N, Stambuk HE. Imaging in oral cancers: A comprehensive review. Oral Oncol 2020; 104:104658. [PMID: 32208340 DOI: 10.1016/j.oraloncology.2020.104658] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2019] [Revised: 03/11/2020] [Accepted: 03/17/2020] [Indexed: 02/08/2023]
Abstract
This review aims at simplifying the relevant imaging anatomy, guiding the optimal imaging method and highlighting the key imaging findings that influence prognosis and management of oral cavity squamous cell carcinoma (OSCC). Early OSCC can be treated with either surgery alone while advanced cancers are treated with a combination of surgery, radiotherapy and/or chemotherapy. Considering the complex anatomy of the oral cavity and its surrounding structures, imaging plays an indispensable role not only in locoregional staging but also in the distant metastatic work-up and post treatment follow-up. Knowledge of the anatomy with understanding of common routes of spread of cancer, allows the radiologist to accurately determine disease extent and augment clinical findings to plan appropriate therapy. This review aims at simplifying the relevant imaging anatomy, guiding the optimal imaging method and highlighting the key imaging findings that influence prognosis and management.
Collapse
Affiliation(s)
- Abhishek Mahajan
- Department of Radiodiagnosis and Imaging, Tata Memorial Hospital, Mumbai 400012, India.
| | - Ankita Ahuja
- Department of Radiodiagnosis and Imaging, Tata Memorial Hospital, Mumbai 400012, India
| | - Nilesh Sable
- Department of Radiodiagnosis and Imaging, Tata Memorial Hospital, Mumbai 400012, India
| | - Hilda E Stambuk
- Department of Radiology, Memorial Sloan-Kettering Cancer Center, 1275 York Avenue, New York, NY 10021, USA
| |
Collapse
|
6
|
Borse V, Konwar AN, Buragohain P. Oral cancer diagnosis and perspectives in India. SENSORS INTERNATIONAL 2020; 1:100046. [PMID: 34766046 PMCID: PMC7515567 DOI: 10.1016/j.sintl.2020.100046] [Citation(s) in RCA: 108] [Impact Index Per Article: 27.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/14/2020] [Revised: 09/19/2020] [Accepted: 09/19/2020] [Indexed: 01/05/2023] Open
Abstract
Globally, oral cancer is the sixth most common type of cancer with India contributing to almost one-third of the total burden and the second country having the highest number of oral cancer cases. Oral squamous cell carcinoma (OSCC) dominates all the oral cancer cases with potentially malignant disorders, which is also recognized as a detectable pre-clinical phase of oral cancer. Tobacco consumption including smokeless tobacco, betel-quid chewing, excessive alcohol consumption, unhygienic oral condition, and sustained viral infections that include the human papillomavirus are some of the risk aspects for the incidence of oral cancer. Lack of knowledge, variations in exposure to the environment, and behavioral risk factors indicate a wide variation in the global incidence and increases the mortality rate. This review describes various risk factors related to the occurrence of oral cancer, the statistics of the distribution of oral cancer in India by various virtues, and the socio-economic positions. The various conventional diagnostic techniques used routinely for detection of the oral cancer are discussed along with advanced techniques. This review also focusses on the novel techniques developed by Indian researchers that have huge potential for application in oral cancer diagnosis.
Collapse
Affiliation(s)
- Vivek Borse
- NanoBioSens Lab, Centre for Nanotechnology, Indian Institute of Technology Guwahati, Guwahati, 781 039, Assam, India
| | - Aditya Narayan Konwar
- NanoBioSens Lab, Centre for Nanotechnology, Indian Institute of Technology Guwahati, Guwahati, 781 039, Assam, India
| | - Pronamika Buragohain
- NanoBioSens Lab, Centre for Nanotechnology, Indian Institute of Technology Guwahati, Guwahati, 781 039, Assam, India
| |
Collapse
|