1
|
Zheng Y, Wang H, Weng T, Li Q, Guo L. Application of convolutional neural network for differentiating ovarian thecoma-fibroma and solid ovarian cancer based on MRI. Acta Radiol 2024; 65:860-868. [PMID: 38751048 DOI: 10.1177/02841851241252951] [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] [Indexed: 05/26/2024]
Abstract
BACKGROUND Ovarian thecoma-fibroma and solid ovarian cancer have similar clinical and imaging features, and it is difficult for radiologists to differentiate them. Since the treatment and prognosis of them are different, accurate characterization is crucial. PURPOSE To non-invasively differentiate ovarian thecoma-fibroma and solid ovarian cancer by convolutional neural network based on magnetic resonance imaging (MRI), and to provide the interpretability of the model. MATERIAL AND METHODS A total of 156 tumors, including 86 ovarian thecoma-fibroma and 70 solid ovarian cancer, were split into the training set, the validation set, and the test set according to the ratio of 8:1:1 by stratified random sampling. In this study, we used four different networks, two different weight modes, two different optimizers, and four different sizes of regions of interest (ROI) to test the model performance. This process was repeated 10 times to calculate the average performance of the test set. The gradient weighted class activation mapping (Grad-CAM) was used to explain how the model makes classification decisions by visual location map. RESULTS ResNet18, which had pre-trained weight, using Adam and one multiple ROI circumscribed rectangle, achieved best performance. The average accuracy, precision, recall, and AUC were 0.852, 0.828, 0.848, and 0.919 (P < 0.01), respectively. Grad-CAM showed areas associated with classification appeared on the edge or interior of ovarian thecoma-fibroma and the interior of solid ovarian cancer. CONCLUSION This study shows that convolution neural network based on MRI can be helpful for radiologists in differentiating ovarian thecoma-fibroma and solid ovarian cancer.
Collapse
Affiliation(s)
- Yuemei Zheng
- Department of Medical Imaging, Affiliated Hospital of Jining Medical University, Jining, PR China
| | - Hong Wang
- Department of Radiology, Tianjin First Central Hospital, Tianjin, PR China
| | - Tingting Weng
- School of Medical Imaging, Tianjin Medical University, Tianjin, PR China
| | - Qiong Li
- Department of Radiology, Tianjin Medical University General Hospital, Tianjin, PR China
| | - Li Guo
- School of Medical Imaging, Tianjin Medical University, Tianjin, PR China
| |
Collapse
|
2
|
Kim HJ, Kim KA, Chun Y, Park YS, Song MJ, Choi JW. Clear Cell Borderline Tumor of the Ovary: A Case Report. JOURNAL OF THE KOREAN SOCIETY OF RADIOLOGY 2023; 84:692-697. [PMID: 37324997 PMCID: PMC10265245 DOI: 10.3348/jksr.2022.0118] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/19/2022] [Revised: 09/12/2022] [Accepted: 10/02/2022] [Indexed: 06/17/2023]
Abstract
Clear cell borderline ovarian tumor (CCBOT) is quite rare, and only a few cases of CCBOT have been reported. Unlike most borderline ovarian tumors, CCBOTs appear solid because they are almost always pathologically adenofibromatous. Herein, we report the MRI findings of a CCBOT discovered in a 22-year-old female.
Collapse
|
3
|
Gagliardi T, Adejolu M, deSouza NM. Diffusion-Weighted Magnetic Resonance Imaging in Ovarian Cancer: Exploiting Strengths and Understanding Limitations. J Clin Med 2022; 11:1524. [PMID: 35329850 PMCID: PMC8949455 DOI: 10.3390/jcm11061524] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2022] [Revised: 03/05/2022] [Accepted: 03/08/2022] [Indexed: 02/06/2023] Open
Abstract
Detection, characterization, staging, and response assessment are key steps in the imaging pathway of ovarian cancer. The most common type, high grade serous ovarian cancer, often presents late, so that accurate disease staging and response assessment are required through imaging in order to improve patient management. Currently, computerized tomography (CT) is the most common method for these tasks, but due to its poor soft-tissue contrast, it is unable to quantify early response within lesions before shrinkage is observed by size criteria. Therefore, quantifiable techniques, such as diffusion-weighted magnetic resonance imaging (DW-MRI), which generates high contrast between tumor and healthy tissue, are increasingly being explored. This article discusses the basis of diffusion-weighted contrast and the technical issues that must be addressed in order to achieve optimal implementation and robust quantifiable diffusion-weighted metrics in the abdomen and pelvis. The role of DW-MRI in characterizing adnexal masses in order to distinguish benign from malignant disease, and to differentiate borderline from frankly invasive malignancy is discussed, emphasizing the importance of morphological imaging over diffusion-weighted metrics in this regard. Its key role in disease staging and predicting resectability in comparison to CT is addressed, including its valuable use as a biomarker for following response within individual lesions, where early changes in the apparent diffusion coefficient in peritoneal metastases may be detected. Finally, the task of implementing DW-MRI into clinical trials in order to validate this biomarker for clinical use are discussed, along with the trials that include it within their protocols.
Collapse
Affiliation(s)
- Tanja Gagliardi
- Department of Imaging, The Royal Marsden NHS Foundation Trust, London SW3 6JJ, UK; (T.G.); (M.A.)
| | - Margaret Adejolu
- Department of Imaging, The Royal Marsden NHS Foundation Trust, London SW3 6JJ, UK; (T.G.); (M.A.)
| | - Nandita M. deSouza
- Department of Imaging, The Royal Marsden NHS Foundation Trust, London SW3 6JJ, UK; (T.G.); (M.A.)
- Division of Radiotherapy and Imaging, The Institute of Cancer Research, London SW7 3RP, UK
| |
Collapse
|
4
|
Kawaguchi M, Kato H, Noda Y, Furui T, Morishige KI, Hyodo F, Matsuo M. Uterine extension determined by MRI: a useful parameter for differentiating subserosal leiomyomas from ovarian tumors. Abdom Radiol (NY) 2022; 47:1142-1149. [PMID: 34994842 DOI: 10.1007/s00261-021-03401-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2021] [Revised: 12/23/2021] [Accepted: 12/24/2021] [Indexed: 12/15/2022]
Abstract
PURPOSE This study aimed to evaluate the utility of uterine extension determined via MRI for the differentiation of large subserosal leiomyomas from ovarian tumors. METHODS In total, 55 patients with subserosal leiomyomas and 127 patients with ovarian tumors were included in this study. These patients were selected from a cohort of female patients whose pelvic masses were larger than 10 cm and who underwent preoperative MRI. We retrospectively reviewed the MRI and compared the diagnostic ability of uterine extension measurements and bridging vascular signs for differentiating subserosal leiomyomas from ovarian tumors. RESULTS The vertical height of the uterus (107.2 ± 36.4 mm vs. 59.9 ± 24.9 mm, p < 0.01), the uterine length (114.4 ± 34.9 mm vs. 80.4 ± 23.8 mm, p < 0.01), and the frequency of the bridging vascular sign (78% vs. 6%, p < 0.01) were significantly higher in subserosal leiomyomas than in ovarian tumors. For diagnosing subserosal leiomyoma, the area under the curve, sensitivity, and specificity of vertical height of the uterus, using cutoff threshold > 81 mm, were 0.89, 89%, and 80% and those of the uterine length, using cutoff threshold > 84 mm, were 0.85, 69%, and 93%, respectively. Alternatively, the sensitivity and specificity of bridging vascular sign were 78% and 94%, respectively. CONCLUSION Uterine extension determined via MRI is a useful parameter for differentiating large subserosal leiomyomas from ovarian tumors.
Collapse
Affiliation(s)
- Masaya Kawaguchi
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan.
| | - Hiroki Kato
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan
| | - Yoshifumi Noda
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan
| | - Tatsuro Furui
- Department of Obstetrics and Gynecology, Gifu University, Gifu, Japan
| | | | - Fuminori Hyodo
- Department of Radiology, Frontier Science for Imaging, Gifu University, Gifu, Japan
| | - Masayuki Matsuo
- Department of Radiology, Gifu University, 1-1 Yanagido, Gifu, 501-1194, Japan
| |
Collapse
|
5
|
Li NY, Shi B, Chen YL, Wang PP, Wang CB, Chen Y, Ge YQ, Dong JN, Wei C. The Value of MRI Findings Combined With Texture Analysis in the Differential Diagnosis of Primary Ovarian Granulosa Cell Tumors and Ovarian Thecoma-Fibrothecoma. Front Oncol 2021; 11:758036. [PMID: 34778075 PMCID: PMC8578857 DOI: 10.3389/fonc.2021.758036] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2021] [Accepted: 10/05/2021] [Indexed: 11/13/2022] Open
Abstract
Objective This study aims to explore the value of magnetic resonance imaging (MRI) and texture analysis (TA) in the differential diagnosis of ovarian granulosa cell tumors (OGCTs) and thecoma-fibrothecoma (OTCA–FTCA). Methods The preoperative MRI data of 32 patients with OTCA–FTCA and 14 patients with OGCTs, confirmed by pathological examination between June 2013 and August 2020, were retrospectively analyzed. The texture data of three-dimensional MRI scans based on T2-weighted imaging and clinical and conventional MRI features were analyzed and compared between tumor types. The Mann–Whitney U-test, χ2 test/Fisher exact test, and multivariate logistic regression analysis were used to identify differences between the OTCA–FTCA and OGCTs groups. A regression model was established by using binary logistic regression analysis, and receiver operating characteristic curve analysis was carried out to evaluate diagnostic efficiency. Results A multivariate analysis of the imaging-based features combined with TA revealed that intratumoral hemorrhage (OR = 0.037), log-sigma-20mm-3D_glszm_SmallAreaEmphasis (OR = 4.40), and log-sigma-2-0mm-3D_glszm_SmallAreaHighGrayLevelEmphasis (OR = 1.034) were independent features for discriminating between OGCTs and OTCA–FTCA (P < 0.05). An imaging-based diagnosis model, TA-based model, and combination model were established. The areas under the curve of the three models in predicting OGCTs and OTCA–FTCA were 0.935, 0.944, and 0.969, respectively; the sensitivities were 93.75, 93.75, and 96.87%, respectively; and the specificities were 85.71, 92.86, and 92.86%, respectively. The DeLong test indicated that the combination model had the highest predictive efficiency (P < 0.05), with no significant difference among the three models in differentiating between OGCTs and OTCA–FTCA (P > 0.05). Conclusions Compared with OTCA–FTCA, intratumoral hemorrhage may be characteristic MR imaging features with OGCTs. Texture features can reflect the microheterogeneity of OGCTs and OTCA–FTCA. MRI signs and texture features can help differentiate between OGCTs and OTCA–FTCA and provide a more comprehensive and accurate basis for clinical treatment.
Collapse
Affiliation(s)
- Nai-Yu Li
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Bin Shi
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Yu-Lan Chen
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Pei-Pei Wang
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Chuan-Bin Wang
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Yao Chen
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Ya-Qiong Ge
- Department of the Healthcare, GE of China, Shanghai, China
| | - Jiang-Ning Dong
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| | - Chao Wei
- The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
| |
Collapse
|
6
|
Zhao SH, Li HM, Qiang JW, Wang DB, Fan H. The value of MRI for differentiating benign from malignant sex cord-stromal tumors of the ovary: emphasis on diffusion-weighted MR imaging. J Ovarian Res 2018; 11:73. [PMID: 30165895 PMCID: PMC6116557 DOI: 10.1186/s13048-018-0444-6] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2018] [Accepted: 08/16/2018] [Indexed: 11/17/2022] Open
Abstract
Background To investigate MRI for differentiating benign from malignant sex cord-stromal tumors of the ovary (SCSTs) emphasizing on the value of diffusion-weighted (DW) magnetic resonance (MR) imaging. Methods This retrospective study included 29 benign SCSTs in 28 patients and 13 malignant SCSTs in 13 patients. DW imaging as well as conventional MR imaging was performed. Signal intensity on DW imaging was assessed and apparent diffusion coefficient (ADC) value was measured. In addition, T2 signal intensity and contrast enhancement pattern were also assessed and compared between benign and malignant SCSTs. Results Both of the T2 hypointensity and mild enhancement were specific to benign SCSTs. The majority of malignant SCSTs showed high signal intensity on DW imaging, whereas most benign SCSTs showed low or moderate signal intensity (p = 0.000). Fibromas were the tumors with the lowest observed ADC value (0.470 × 10− 3 mm2/s). Sclerosing stromal tumors were the tumors with the highest observed ADC value (2.291 × 10− 3 mm2/s). ADC value of solid component was significantly lower in malignant SCSTs (0.825 ± 0.129 × 10− 3 mm2/s) than in benign SCSTs (1.343 ± 0.528 × 10− 3 mm2/s) when fibromas were excluded (p = 0.024). T2, DCE and DW imaging has a limited value on the differential diagnosis of the benign and malignant SCSTs with an accuracy of 69.0%,71.4% and 78.1% respectively. Combination of T2, DCE and DW imaging permitted the distinction with an accuracy of 88.0%. Conclusions It is more helpful for distinction of the benign and malignant SCSTs by combining of T2, DCE and DW imaging than using each of the three sequences independently.
Collapse
Affiliation(s)
- Shu-Hui Zhao
- Department of Radiology, Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine, 1665 Kongjiang Road, Shanghai, 200092, China
| | - Hai-Ming Li
- Department of Radiology, Jinshan Hospital, Fudan University, 1508 Longhang Road, Shanghai, 201508, China
| | - Jin-Wei Qiang
- Department of Radiology, Jinshan Hospital, Fudan University, 1508 Longhang Road, Shanghai, 201508, China.
| | - Deng-Bin Wang
- Department of Radiology, Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine, 1665 Kongjiang Road, Shanghai, 200092, China.
| | - Hua Fan
- Department of Radiology, Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine, 1665 Kongjiang Road, Shanghai, 200092, China
| |
Collapse
|
7
|
Chen J, Wang J, Chen X, Wang Y, Wang Z, Li D. Computed tomography and magnetic resonance imaging features of ovarian fibrothecoma. Oncol Lett 2017; 14:1172-1178. [PMID: 28693292 DOI: 10.3892/ol.2017.6228] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2016] [Accepted: 03/17/2017] [Indexed: 01/04/2023] Open
Abstract
The aim of the present study was to investigate the imaging characteristics of ovarian fibrothecoma. The cases of 25 female patients with pathologically confirmed ovarian fibrothecomas were retrospectively reviewed. Tumor location, size, density, signal intensity, cystic degeneration, calcification, enhancement pattern and ascites were assessed by computed tomography (CT) (n=20) and magnetic resonance imaging (MRI) (n=5). Clinical and histological features were also evaluated. The results revealed that 23 (92.0%) patients were postmenopausal, with a mean age ± standard deviation (SD) of 60.7±10.8 years old. All 25 tumors were unilateral and a thickened endometrium was observed in 7 (28.0%) patients. In total, 24 (96.0%) tumors appeared to have well-defined boundaries, with 1 (4%) tumor exhibiting an obscure boundary. Tumors had a mean size of 9.8±5.3 cm. Solid and predominantly solid masses were found in 16 cases (64.0%), and cystic and predominantly cystic masses were found in 9 patients (36.0%). Solid regions of masses exhibited hypodensity or isodensity in 24 patients (96.0%), with 1 patient (4.0%) exhibiting hyperdensity. The mean CT value (± SD) was 44.2±12.8 HU (range, 31-79HU) in unenhanced images. All masses exhibited isointensity or slight hypointensity on T1-weighted imaging, and tumor parenchyma also exhibited slight hypointensity or isointensity on T2-weighted imaging compared with the myometrium, with or without areas of patchy hyperintensity. Contrast-enhanced CT or MRI scans were performed on 19 patients, and the solid components (94.7%) exhibited mild to moderate enhancement in 18 patients and 1 patient (5.3%) exhibited intense enhancement. Tumor size was positively correlated with the tumor cystic degeneration (r=0.77, P<0.001) and ascites (r=0.41, P<0.001). Therefore, ovarian fibrothecoma typically presents as solid or predominant solid masses with clear boundaries; the parenchyma of the tumor exhibits isodensity on CT scans, slight hypointensity or isointensity on MRI and mild enhancement following contrast-medium injection. The thickened endometrium observed in postmenopausal woman may also be a valuable imaging feature.
Collapse
Affiliation(s)
- Jingya Chen
- Department of Radiology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210029, P.R. China
| | - Jianhua Wang
- Department of Radiology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210029, P.R. China
| | - Xiao Chen
- Department of Radiology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210029, P.R. China
| | - Yaohui Wang
- Department of Pathology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210029, P.R. China
| | - Zhongqiu Wang
- Department of Radiology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210029, P.R. China
| | - Dake Li
- Department of Gynecology, Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, Jiangsu 210029, P.R. China
| |
Collapse
|
8
|
Cho YJ, Lee HS, Kim JM, Lee SY, Song T, Seong SJ, Kim ML. Ovarian-sparing local mass excision for ovarian fibroma/fibrothecoma in premenopausal women. Eur J Obstet Gynecol Reprod Biol 2014; 185:78-82. [PMID: 25528734 DOI: 10.1016/j.ejogrb.2014.11.042] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2014] [Revised: 11/19/2014] [Accepted: 11/27/2014] [Indexed: 11/15/2022]
Abstract
OBJECTIVES To evaluate the recurrence rate of ovarian fibroma/fibrothecoma and reproductive outcomes following ovarian-sparing local mass excision in premenopausal women. STUDY DESIGN A retrospective cohort study was performed at two gynecologic surgery centers using data collected between January 2005 and December 2011. It included premenopausal patients treated with ovarian-sparing local mass excision and pathologically proven ovarian fibroma/fibrothecoma who were followed up for at least 6 months. The recurrence of fibroma/fibrothecoma and pregnancy outcomes in those who wanted to conceive after local mass excision were collected and analyzed. RESULTS The mean age of the patients (n=50) was 33.3±6.9 years (range, 20-50 years), and the mean follow-up duration was 26.6±19.2 months (range, 6-88 months). Fibroma was present in 40 patients, fibrothecoma in 7, and cellular fibroma in 3. Natural conception occurred in 11 of the 12 patients who became pregnant during the follow-up period. On follow-up ultrasonography, one patient experienced recurrent disease, 50 months after initial surgery, resulting in a crude overall recurrence rate of only 2%. CONCLUSION Given the 2% recurrence rate of ovarian fibroma/fibrothecoma following ovarian sparing local mass excision, local mass excision appears to be an effective surgical option in women of reproductive age.
Collapse
Affiliation(s)
- Yeon Jean Cho
- Department of Obstetrics and Gynecology, Dong-A University Medical Center, Dong-A University, College of Medicine, Busan, Republic of Korea
| | - Hee Suk Lee
- Department of Obstetrics and Gynecology, Dong-A University Medical Center, Dong-A University, College of Medicine, Busan, Republic of Korea
| | - Joo Myung Kim
- Department of Obstetrics and Gynecology, Cheil General Hospital and Women's Healthcare Center, Kwandong University College of Medicine, Seoul, Republic of Korea
| | - Soo Yoon Lee
- Department of Obstetrics and Gynecology, Cheil General Hospital and Women's Healthcare Center, Kwandong University College of Medicine, Seoul, Republic of Korea
| | - Taejong Song
- Department of Obstetrics and Gynecology, Kangbuk Samsung Hospital, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea
| | - Seok Ju Seong
- Department of Obstetrics and Gynecology, CHA Gangnam Medical Center, CHA University, Seoul, Republic of Korea
| | - Mi-La Kim
- Department of Obstetrics and Gynecology, CHA Gangnam Medical Center, CHA University, Seoul, Republic of Korea.
| |
Collapse
|