1
|
Wang G, Sun Y, Jiang S, Wu G, Liao W, Chen Y, Lin Z, Liu Z, Zhuo S. Machine learning-based rapid diagnosis of human borderline ovarian cancer on second-harmonic generation images. BIOMEDICAL OPTICS EXPRESS 2021; 12:5658-5669. [PMID: 34692207 PMCID: PMC8515988 DOI: 10.1364/boe.429918] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/26/2021] [Revised: 08/09/2021] [Accepted: 08/09/2021] [Indexed: 05/30/2023]
Abstract
Regarding growth pattern and cytological characteristics, borderline ovarian tumors fall between benign and malignant, but they tend to develop malignancy. Currently, it is difficult to accurately diagnose ovarian cancer using common medical imaging methods, and histopathological examination is routinely used to obtain a definitive diagnosis. However, such examination requires experienced pathologists, being labor-intensive, time-consuming, and possibly leading to interobserver bias. By using second-harmonic generation imaging and k-nearest neighbors classifier in conjunction with automated machine learning tree-based pipeline optimization tool, we developed a computer-aided diagnosis method to classify ovarian tissues as being malignant, benign, borderline, and normal, obtaining areas under the receiver operating characteristic curve of 1.00, 0.99, 0.98, and 0.97, respectively. These results suggest that diagnosis based on second-harmonic generation images and machine learning can support the rapid and accurate detection of ovarian cancer in clinical practice.
Collapse
Affiliation(s)
- Guangxing Wang
- School of Science, Jimei University, Xiamen 361021, China
- State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics, Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen 361102, China
- These authors contributed equally
| | - Yang Sun
- Department of Gynecology, Fujian Medical University Cancer Hospital, Fujian Cancer Hospital, Fuzhou 350014, China
- These authors contributed equally
| | - Shuisen Jiang
- School of Science, Jimei University, Xiamen 361021, China
| | - Guizhu Wu
- Shanghai First Maternity and Infant Hospital, Tongji University School of Medicine, Shanghai 200030, China
| | - Wenliang Liao
- School of Science, Jimei University, Xiamen 361021, China
| | - Yuwei Chen
- Department of Gynecology, Fujian Medical University Cancer Hospital, Fujian Cancer Hospital, Fuzhou 350014, China
| | - Zexi Lin
- Key Laboratory of OptoElectronic Science and Technology for Medicine of the Ministry of Education & Fujian Provincial Key Laboratory of Photonics Technology, Fujian Normal University, Fuzhou, 350007, China
| | - Zhiyi Liu
- State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou 310058, China
| | - Shuangmu Zhuo
- School of Science, Jimei University, Xiamen 361021, China
| |
Collapse
|
2
|
Kępka L, Bujko K, Bujko M, Matecka-Nowak M, Salata A, Janowski H, Rogowska D, Cieślak-Żerańska E, Komosińska K, Zawadzka A. Target volume for postoperative radiotherapy in non-small cell lung cancer: results from a prospective trial. Radiother Oncol 2013; 108:61-5. [PMID: 23791302 DOI: 10.1016/j.radonc.2013.05.023] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2013] [Revised: 05/14/2013] [Accepted: 05/26/2013] [Indexed: 12/12/2022]
Abstract
BACKGROUND AND PURPOSE A previous prospective trial reported that three-dimensional conformal postoperative radiotherapy (PORT) for pN2 NSCLC patients using a limited clinical target volume (CTV) had a late morbidity rate and pulmonary function that did not differ from those observed in pN1 patients treated with surgery without PORT. The aim of this study was to assess locoregional control and localization of failure in patients treated with PORT. MATERIALS AND METHODS The pattern of locoregional failure was evaluated retrospectively in 151 of 171 patients included in the PORT arm. The CTV included the involved lymph node stations and those with a risk of invasion >10%. Competing risk analysis was used to assess the incidence of locoregional failure and its location outside the CTV. RESULTS Overall survival at 5years was 27.1% with a median follow-up of 67months for 40 living patients. The 5-year cumulative incidence of locoregional failure was 19.4% (95% CI: 18.2-20.5%) including a failure rate of 2% (95% CI: 0-17%) in locations outside or at the border of the CTV. CONCLUSIONS The use of limited CTV was associated with acceptable risk of geographic miss. Overall locoregional control was similar to that reported by other studies using PORT for pN2 patients.
Collapse
Affiliation(s)
- Lucyna Kępka
- Department of Radiotherapy, The Maria Sklodowska-Curie Memorial Cancer Centre and Institute of Oncology, Warsaw, Poland.
| | | | | | | | | | | | | | | | | | | |
Collapse
|