Development of deep learning model for diagnosing muscle-invasive bladder cancer on MRI with vision transformer.

Rationale and objectives: To develop and validate a deep learning (DL) model to automatically diagnose muscle-invasive bladder cancer (MIBC) on MRI with Vision Transformer (ViT). Materials and methods: This multicenter retrospective study included patients with BC who reported to two institutions between January 2016 and June 2020 (training dataset) and a third institution between May 2017 and May 2022 (test dataset). The diagnostic model for MIBC and the segmentation model for BC on MRI were developed using the training dataset with 5-fold cross-validation. ViT- and convolutional neural network (CNN)-based diagnostic models were developed and compared for diagnostic performance using the area under the curve (AUC). The performance of the diagnostic model with manual and auto-generated regions of interest (ROImanual and ROIauto, respectively) was validated on the test dataset and compared to that of radiologists (three senior and three junior radiologists) using Vesical Imaging Reporting and Data System scoring. Results: The training and test datasets included 170 and 53 patients, respectively. Mean AUC of the top 10 ViT-based models with 5-fold cross-validation outperformed those of the CNN-based models (0.831 ± 0.003 vs. 0.713 ± 0.007-0.812 ± 0.006, p < .001). The diagnostic model with ROImanual achieved AUC of 0.872 (95 % CI: 0.777, 0.968), which was comparable to that of junior radiologists (AUC = 0.862, 0.873, and 0.930). Semi-automated diagnosis with the diagnostic model with ROIauto achieved AUC of 0.815 (95 % CI: 0.696, 0.935). Conclusion: The DL model effectively diagnosed MIBC. The ViT-based model outperformed CNN-based models, highlighting its utility in medical image analysis.

Investigation of the clinical implications of anterior cervical invasion in locally advanced cervical squamous cell carcinoma.

PURPOSES: This study investigates the clinical significance of the anterior parametrical invasion in surgically treated patients with cervical squamous cell carcinoma (SCC). METHODS: We included patients diagnosed with cervical SCC with local lesions classified as T2b, who were treated at our department between January 2006 and December 2020. We evaluated the degree of anterior invasion using pretreatment magnetic resonance imaging and divided patients into three groups: partial, equivocal, and full invasion. The frequency of recurrence within 3 years (early recurrence) and overall prognosis were assessed. RESULTS: There were 12, 24, and 46 cases in the partial equivocal, and full invasion groups, respectively. Neoadjuvant chemotherapy followed by surgery and adjuvant chemotherapy was the mainstay of treatment across all groups (7, 17, and 27 cases, respectively). Although the frequency of early recurrence tended to be worse in the full group (partial; 2/7 cases, equivocal; 3/17 cases and full; 9/27 cases), all early local recurrence cases in the full group (four cases) responded well to the subsequent treatment. As for overall survival, the full invasion group had the best prognosis among the three groups. CONCLUSIONS: In surgical treatment, although full anterior invasion may increase the risk of early local recurrence, it was considered to have little prognostic impact.

Magnetic resonance imaging features of complete androgen insensitivity syndrome in comparison to Mayer-Rokitansky-Küster-Hauser syndrome.

PURPOSE: Complete androgen insensitivity syndrome (CAIS) and Mayer-Rokitansky-Küster-Hauser syndrome (MRKHS) share common clinical features such as female phenotype, vaginal hypoplasia, and primary amenorrhea. Magnetic resonance imaging (MRI) is performed to investigate the cause of primary amenorrhea. However, the MRI features are also similar in both disorders. They are ultimately diagnosed by chromosome testing, but there is a possibility of misdiagnosis if chromosome testing is not performed. This study aimed to identify MRI features that are useful for differentiating CAIS from MRKHS. METHOD: This multicenter retrospective study included 12 patients with CAIS and 19 patients with MRKHS. Three radiologists blindly evaluated the following features: (1) detection of vagina, (2) detection of nodular and cystic structures in the lateral pelvis; undescended testicles and paratesticular cysts in CAIS and rudimentary uteri and ovaries in MRKHS, (3) their location, (4) number of cysts in the cystic structures, and (5) signal intensity on diffusion-weighted images (DWI) and apparent diffusion coefficient (ADC) values of the nodular structures. Statistical comparisons were performed using Mann-Whitney U and Fisher's exact tests. RESULTS: Compared with MRKHS, the CAIS group showed significantly detectable vagina, more ventrally located nodular and cystic structures, fewer cysts within the cystic structures, and nodular structures with higher signal intensity on DWI and lower ADC values. CONCLUSIONS: MRI features of detectable vagina, location of nodular and cystic structures, number of cysts within the cystic structures, signal intensity on DWI and ADC values of the nodular structures were useful in differentiating CAIS from MRKHS.

Preoperative Imaging Evaluation of Endometrial Cancer in FIGO 2023.

The staging of endometrial cancer is based on the International Federation of Gynecology and Obstetrics (FIGO) staging system according to the examination of surgical specimens, and has revised in 2023, 14 years after its last revision in 2009. Molecular and histological classification has incorporated to new FIGO system reflecting the biological behavior and prognosis of endometrial cancer. Nonetheless, the basic role of imaging modalities including ultrasound, computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography, as a preoperative assessment of the tumor extension and also the evaluation points in CT and MRI imaging are not changed, other than several point of local tumor extension. In the field of radiology, it has also undergone remarkable advancement through the rapid progress of computational technology. The application of deep learning reconstruction techniques contributes the benefits of shorter acquisition time or higher quality. Radiomics, which extract various quantitative features from the images, is also expected to have the potential for the quantitative prediction of risk factors such as histological types and lymphovascular space invasion, which is newly included in the new FIGO system. This article reviews the preoperative imaging diagnosis in new FIGO system and recent advances in imaging analysis and their clinical contributions in endometrial cancer. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 3.

Nodal infiltration in endometrial cancer: a prediction model using best subset regression.

OBJECTIVES: To build preoperative prediction models with and without MRI for regional lymph node metastasis (r-LNM, pelvic and/or para-aortic LNM (PENM/PANM)) and for PANM in endometrial cancer using established risk factors. METHODS: In this retrospective two-center study, 364 patients with endometrial cancer were included: 253 in the model development and 111 in the external validation. For r-LNM and PANM, respectively, best subset regression with ten-time fivefold cross validation was conducted using ten established risk factors (4 clinical and 6 imaging factors). Models with the top 10 percentile of area under the curve (AUC) and with the fewest variables in the model development were subjected to the external validation (11 and 4 candidates, respectively, for r-LNM and PANM). Then, the models with the highest AUC were selected as the final models. Models without MRI findings were developed similarly, assuming the cases where MRI was not available. RESULTS: The final r-LNM model consisted of pelvic lymph node (PEN) ≥ 6 mm, deep myometrial invasion (DMI) on MRI, CA125, para-aortic lymph node (PAN) ≥ 6 mm, and biopsy; PANM model consisted of DMI, PAN, PEN, and CA125 (in order of correlation coefficient ß values). The AUCs were 0.85 (95%CI: 0.77-0.92) and 0.86 (0.75-0.94) for the external validation, respectively. The model without MRI for r-LNM and PANM showed AUC of 0.79 (0.68-0.89) and 0.87 (0.76-0.96), respectively. CONCLUSIONS: The prediction models created by best subset regression with cross validation showed high diagnostic performance for predicting LNM in endometrial cancer, which may avoid unnecessary lymphadenectomies. CLINICAL RELEVANCE STATEMENT: The prediction risks of lymph node metastasis (LNM) and para-aortic LNM can be easily obtained for all patients with endometrial cancer by inputting the conventional clinical information into our models. They help in the decision-making for optimal lymphadenectomy and personalized treatment. KEY POINTS: •Diagnostic performance of lymph node metastases (LNM) in endometrial cancer is low based on size criteria and can be improved by combining with other clinical information. •The optimized logistic regression model for regional LNM consists of lymph node ≥ 6 mm, deep myometrial invasion, cancer antigen-125, and biopsy, showing high diagnostic performance. •Our model predicts the preoperative risk of LNM, which may avoid unnecessary lymphadenectomies.

A case of paraovarian tumor of borderline malignancy with decrease of apparent diffusion coefficient value and marked 18F-fluorodeoxyglucose accumulation.

Para-ovarian cysts are occasionally encountered in clinical practice; however, malignant tumors derived from them are rare. Due to its rarity, the characteristic imaging findings of para-ovarian tumors with borderline malignancy (PTBM) are largely unknown. Herein, we report a case of PTBM, along with imaging findings. A 37-year-old woman came to our department with a suspected malignant adnexal tumor. Pelvic contrast-enhanced magnetic resonance imaging (MRI) revealed a solid part within the cystic tumor with a decrease in the apparent diffusion coefficient (ADC) value (1.16 × 10-3 mm2/s). We also performed Positron Emission Tomography-MRI and showed a strong accumulation of 18F-fluorodeoxyglucose (FDG) in the solid part (SUVmax = 14.8). In addition, the tumor appeared to develop independently of the ovary. Because tumor was derived from para-ovarian cyst, we suspected PTBM preoperatively and planned fertility sparing treatment. Pathological examination revealed a serous borderline tumor and PTBM was confirmed. PTBM can have unique imaging characteristics, including a low ADC value and high FDG accumulation. When a tumor appears to develop from para-ovarian cysts, borderline malignancy can be suspected, even if imaging findings suggest malignant potential.

Automatic segmentation of bladder cancer on MRI using a convolutional neural network and reproducibility of radiomics features: a two-center study.

This study aimed to develop a versatile automatic segmentation model of bladder cancer (BC) on MRI using a convolutional neural network and investigate the robustness of radiomics features automatically extracted from apparent diffusion coefficient (ADC) maps. This two-center retrospective study used multi-vendor MR units and included 170 patients with BC, of whom 140 were assigned to training datasets for the modified U-net model with five-fold cross-validation and 30 to test datasets for assessment of segmentation performance and reproducibility of automatically extracted radiomics features. For model input data, diffusion-weighted images with b = 0 and 1000 s/mm2, ADC maps, and multi-sequence images (b0-b1000-ADC maps) were used. Segmentation accuracy was compared between ours and existing models. The reproducibility of radiomics features on ADC maps was evaluated using intraclass correlation coefficient. The model with multi-sequence images achieved the highest Dice similarity coefficient (DSC) with five-fold cross-validation (mean DSC = 0.83 and 0.79 for the training and validation datasets, respectively). The median (interquartile range) DSC of the test dataset model was 0.81 (0.70-0.88). Radiomics features extracted from manually and automatically segmented BC exhibited good reproducibility. Thus, our U-net model performed highly accurate segmentation of BC, and radiomics features extracted from the automatic segmentation results exhibited high reproducibility.