Association between comorbidities and survival in patients with metastatic urothelial carcinoma treated with pembrolizumab.

BACKGROUND: This study aims to investigate the relationship between comorbidities and survival in patients with mUC treated with pembrolizumab as a second-line treatment. METHODS: From February 2018 to October 2021, we analyzed the data of 185 consecutive patients with metastatic UC who received pembrolizumab as second-line therapy at The Jikei University Hospital and five affiliated hospitals. We used the Charlson Comorbidity Index (CCI) to assess the comorbidities. The outcomes of interest were progression-free survival (PFS) and overall survival (OS). To compare the survival differences, inverse probability of treatment weighting (IPTW)-adjusted Kaplan-Meier curves and the IPTW-adjusted Cox regression hazards model were used. RESULTS: After IPTW adjustment, patient characteristics were well-balanced between patients with high CCI and those with low CCI. The IPTW-adjusted Kaplan-Meier curves of PFS and OS based on CCI revealed that the patients with high CCI (2 or more) had a shorter PFS (median, 1.6 vs. 2.8 months) and a shorter OS (median, 12.4 vs. 18.8 months) (0-1). Similarly, in the IPTW-adjusted Cox regression hazards model, patients with high CCI had significantly shorter PFS [HR, 1.84 (95% CI 1.26-2.68; p = 0.002)] and OS [HR, 1.98 (95% CI 1.20-3.27; p = 0.008)] than those with lower CCI. CONCLUSIONS: High CCI was associated with a higher risk of disease progression as well as overall mortality in mUC patients treated with second-line pembrolizumab.

Real world evidence of enfortumab vedotin in patients with advanced urothelial cancer: A multicenter observational study.

OBJECTIVES: To explore the characteristics of patients and assess the effectiveness of enfortumab vedotin (EV) in those with treatment-resistant advanced urothelial cancer in a real-world setting. PATIENTS AND METHODS: A multicenter observational study was conducted on 103 evaluable patients with advanced urothelial cancer who received EV. Outcomes were assessed by radiographic response, progression-free survival (PFS), and overall survival (OS), with treatment-related adverse events (trAEs). Radiographic response was assessed using Response Evaluation Criteria in Solid Tumors version 1.1, while trAEs were studied in line with Common Terminology Criteria for Adverse Events version 5.0. RESULTS: The median follow-up was 8.9 months (range, 0.1-16.4). The observed objective response rate was 50.5%. The median PFS was 6.0 months (95% CI: 4.7-9.8), and the median OS was 14.5 months (95% CI: 12.4-not reached). Out of the 103 patients, 19 (18.4%) had an Eastern Cooperative Oncology Group performance status of 2 or more, 14 (14.7%) had an non-urothelial carcinoma histology, and 40 (38.3%) had at least one pre-existing comorbidity. There were 26 (25.2%) patients who reported 49 trAEs, with 9 (18.3%) being grade 3 or higher. The most common trAEs included rash, occurring in 18.4%. CONCLUSIONS: This study describes the characteristics and outcomes of patients with previously treated advanced urothelial cancer receiving EV. The findings demonstrate that EV showed robust anti-tumor activity and had manageable safety profiles outside the clinical trial setting.

Effectiveness of pembrolizumab in trial-ineligible patients with metastatic urothelial carcinoma.

BACKGROUND: The KEYNOTE-045 trial showed that pembrolizumab therapy improved the survival of patients with advanced urothelial carcinoma (UC). However, its effectiveness in trial-ineligible patients remains unclear. MATERIALS AND METHODS: We conducted a multicenter retrospective study to evaluate the effectiveness of pembrolizumab in patients with metastatic UC who were trial-ineligible. The data of 164 consecutive patients with platinum-treated metastatic UC who received pembrolizumab as second-line therapy were analyzed. Trial eligibility was assessed using the KEYNOTE-045 criteria. Inverse probability of treatment weighting (IPTW) was used to balance patient characteristics. Overall survival (OS) and progression-free survival (PFS) were examined using the IPTW-adjusted Kaplan-Meier method. IPTW-adjusted restricted mean survival times (RMSTs) were compared between ineligible and eligible patients. RESULTS: Seventy-five patients (45.7%) were classified as ineligible based on the KEYNOTE-045 criteria. Baseline hemoglobin concentration of less than 9.0 g/dL was the most common reason for trial protocol violation (N = 23 [14.0%]). An IPTW-adjusted logistic regression model showed that the trial-eligibility was not significantly associated with objective response (OR: 0.65, 95% CI: 0.32 to 1.29, P = 0.22). Ineligible patients had similar RMST for PFS (difference: 3.8 months, 95% CI: -1.6 to 9.3, P = 0.17) and RMST for OS (difference: 1.4 months, 95% CI: -5.4 to 8.2, P = 0.93) compared with eligible patients. CONCLUSIONS: This study suggests that the effectiveness of pembrolizumab may be retained in ineligible patients with platinum-treated metastatic UC. Expanding trial eligibility criteria for these patients may be beneficial.

Comparison of neoadjuvant and adjuvant chemotherapy for upper tract urothelial carcinoma in real-world practice: a multicenter retrospective study.

BACKGROUND: Multiple studies have demonstrated the effectiveness of neoadjuvant chemotherapy and adjuvant chemotherapy in patients with upper tract urothelial carcinoma compared with surgery alone. However, no clinical trial has established the superiority of neoadjuvant chemotherapy or adjuvant chemotherapy in terms of perioperative outcomes. METHODS: We conducted a retrospective analysis encompassing 164 upper tract urothelial carcinoma patients who underwent radical nephroureterectomy and received perioperative chemotherapy. Of these patients, 65 (39.6%) and 99 (60.4%) received neoadjuvant chemotherapy and adjuvant chemotherapy, respectively. Recurrence-free survival and cancer-specific survival were computed using the Kaplan-Meier method. Additionally, we conducted Cox regression analyses to evaluate the risk factors for recurrence-free survival and cancer-specific survival. RESULTS: Pathological downstaging was seen in 37% of the neoadjuvant chemotherapy group. However, no pathological complete response was observed in this cohort. The Kaplan-Meier curves demonstrated significantly lower recurrence-free survival and cancer-specific survival in patients who received adjuvant chemotherapy. Multivariate Cox regression analysis revealed patients treated with adjuvant chemotherapy exhibited a marked association with inferior recurrence-free survival and cancer-specific survival. CONCLUSION: Our study has suggested that neoadjuvant chemotherapy would be more effective in high-risk upper tract urothelial carcinoma patients compared with adjuvant chemotherapy.

Clinical benefit of continuing pembrolizumab treatment beyond progression in patients with metastatic urothelial carcinoma.

BACKGROUND: There has been no clinical evidence to justify continued pembrolizumab therapy beyond progression in patients with metastatic urothelial carcinoma (UC). MATERIALS AND METHODS: We conducted a multicenter retrospective study evaluating the clinical efficacy of continued use of pembrolizumab beyond progression in patients with metastatic UC. Data from 51 patients with metastatic UC, who developed progression during second-line pembrolizumab therapy, were analyzed. Progression was defined based on the Immunotherapy Response Evaluation Criteria in Solid Tumors. The outcome was overall survival (OS). The association between continued treatment, OS, and the risk of all-cause mortality was tested using log-rank test, conventional and time-dependent Cox regression models. RESULTS: No significant difference in patient characteristics was noted between patients continuing pembrolizumab beyond progression (N = 21) and those discontinuing pembrolizumab (N = 30). Median OS was significantly longer in the continuation group (17.8 vs. 8.8 months; P = 0.038). A multivariable conventional Cox regression model identified continued pembrolizumab administration as a significant independent prognostic factor of all-cause mortality (hazard ratio [HR]: 0.21, 95% confidence interval [CI]: 0.05-0.90, P = 0.036), irrespective of the time from treatment initiation to progression and concurrent clinical progression. Further, longer duration of pembrolizumab treatment beyond progression was independently associated with a reduced risk of all-cause mortality in a multivariable time-dependent Cox regression model, when used as a time-dependent variable (HR: 0.07, 95% CI: 0.01-0.45, P = 0.006). CONCLUSIONS: Continued pembrolizumab administration beyond progression might be beneficial in patients with metastatic UC who were clinically stable.

Comparison of the Immunotherapy Response Evaluation Criteria in Solid Tumours (iRECIST) with RECIST for capturing treatment response of patients with metastatic urothelial carcinoma treated with pembrolizumab.

OBJECTIVE: To evaluate the clinical usefulness of Immunotherapy Response Evaluation Criteria in Solid Tumours (iRECIST) in patients with metastatic urothelial carcinoma (UC) treated with pembrolizumab. The iRECIST is designed to accurately capture the tumour response treated with immunotherapy. PATIENTS AND METHODS: We conducted a multicentre retrospective study evaluating the clinical utility of iRECIST in 91 patients with metastatic UC treated with second-line pembrolizumab. The objective response (OR) and time to progression (TTP) in accordance with both iRECIST and RECIST version 1.1 were compared with overall survival (OS) and risk of all-cause mortality, and analysed using log-rank and multivariable Cox regression models, respectively. Predictive performance of the criteria was studied using Harrell's concordance index (c-index). The clinical usefulness of each criterion was compared using decision curve analysis. RESULTS: Of 57 patients with progressive disease per RECIST, a considerable number of patients were reclassified to immune stable disease (six, 10.5%), immune partial response (two, 3.5%), and immune complete response (two, 3.5%) per iRECIST. Multivariable Cox regression models showed that both OR (hazard ratio [HR] 0.10, 95% confidence interval [CI] 0.03-0.35; P = 0.001) and TTP (HR 0.59, 95% CI 0.46-0.77; P < 0.001) per iRECIST were significantly associated with all-cause mortality. Furthermore, iRECIST had a significant, increased predictability of OS compared with RECIST (OR, c-index: 0.70, increase: 0.04, P = 0.046; TTP, c-index: 0.88, increase: 0.07, P = 0.039). On decision curve analysis, iRECIST presented better net benefit gains than did RECIST. CONCLUSIONS: Compared with RECIST, iRECIST could more accurately predict OS of patients with metastatic UC treated with pembrolizumab. The iRECIST has the potential to be a new standard for tumour response evaluation of these patients.

Artificial intelligence-based image-domain material decomposition in single-energy computed tomography for head and neck cancer.

PURPOSE: While dual-energy computed tomography (DECT) images provide clinically useful information than single-energy CT (SECT), SECT remains the most widely used CT system globally, and only a few institutions can use DECT. This study aimed to establish an artificial intelligence (AI)-based image-domain material decomposition technique using multiple keV-output learning of virtual monochromatic images (VMIs) to create DECT-equivalent images from SECT images. METHODS: This study involved 82 patients with head and neck cancer. Of these, the AI model was built with data from the 67 patients with only DECT scans, while 15 patients with both SECT and DECT scans were used for SECT testing. Our AI model generated VMI50keV and VMI100keV from VMI70keV equivalent to 120-kVp SECT images. We introduced a loss function for material density images (MDIs) in addition to the loss for VMIs. For comparison, we trained the same model with the loss for VMIs only. DECT-equivalent images were generated from SECT images and compared with the true DECT images. RESULTS: The prediction time was 5.4 s per patient. The proposed method with the MDI loss function quantitatively provided more accurate DECT-equivalent images than the model trained with the loss for VMIs only. Using real 120-kVp SECT images, the trained model produced precise DECT images of excellent quality. CONCLUSION: In this study, we developed an AI-based material decomposition approach for head and neck cancer patients by introducing the loss function for MDIs via multiple keV-output learning. Our results suggest the feasibility of AI-based image-domain material decomposition in a conventional SECT system without a DECT scanner.

Synthetic Low-Energy Monochromatic Image Generation in Single-Energy Computed Tomography System Using a Transformer-Based Deep Learning Model.

While dual-energy computed tomography (DECT) technology introduces energy-specific information in clinical practice, single-energy CT (SECT) is predominantly used, limiting the number of people who can benefit from DECT. This study proposed a novel method to generate synthetic low-energy virtual monochromatic images at 50 keV (sVMI50keV) from SECT images using a transformer-based deep learning model, SwinUNETR. Data were obtained from 85 patients who underwent head and neck radiotherapy. Among these, the model was built using data from 70 patients for whom only DECT images were available. The remaining 15 patients, for whom both DECT and SECT images were available, were used to predict from the actual SECT images. We used the SwinUNETR model to generate sVMI50keV. The image quality was evaluated, and the results were compared with those of the convolutional neural network-based model, Unet. The mean absolute errors from the true VMI50keV were 36.5 ± 4.9 and 33.0 ± 4.4 Hounsfield units for Unet and SwinUNETR, respectively. SwinUNETR yielded smaller errors in tissue attenuation values compared with those of Unet. The contrast changes in sVMI50keV generated by SwinUNETR from SECT were closer to those of DECT-derived VMI50keV than the contrast changes in Unet-generated sVMI50keV. This study demonstrated the potential of transformer-based models for generating synthetic low-energy VMIs from SECT images, thereby improving the image quality of head and neck cancer imaging. It provides a practical and feasible solution to obtain low-energy VMIs from SECT data that can benefit a large number of facilities and patients without access to DECT technology.

Comparison of the efficacy of enfortumab vedotin between patients with metastatic urothelial carcinoma who were treated with avelumab or pembrolizumab: real-world data from a multi-institutional study in Japan.

OBJECTIVES: Enfortumab vedotin (EV) is a novel antibody-drug conjugate approved for metastatic urothelial carcinoma (UC) refractory to prior treatment with immune checkpoint inhibitors (ICIs). However, the difference in efficacy of EV after each ICIs and prognostic factors are not well known. We aimed to compare the efficacy of EV in patients with metastatic UC who were treated with avelumab or pembrolizumab and to identify the prognostic factors. METHODS: The records of 100 patients with advanced metastatic UC who received EV after the administration of either avelumab or pembrolizumab were retrospectively collected from five academic hospitals in Japan. RESULTS: The median follow-up period was 6.7 months. The median overall survival (OS) and progression-free survival (PFS) in the EV after avelumab/pembrolizumab group were not reached/14.7 months (p = 0.17) and 10.4/5.2 months (p = 0.039), respectively. The objective response rates (ORR) were 66.6% and 46.8% in EV after avelumab and EV after pembrolizumab groups, respectively (p = 0.14). Multivariate analysis identified histological variants, liver metastasis, low serum albumin levels, and high serum CRP level as significant poor prognostic factors. The median OS and PFS of cachexia patients with both low serum albumin levels and high serum CRP levels were 6.0 months and 0.93 months, respectively. CONCLUSION: PFS was superior in patients treated with EV after avelumab to EV after pembrolizumab. However, OS showed no significant difference between the two groups. Because the prognosis of patients with cachexia is extremely poor, the initiation of EV should be discussed in these patients.

Single-Fraction Palliative High-Dose-Rate Brachytherapy for Symptom Management in a 97-Year-Old Patient With Dementia.

Background: Delivering cancer treatment to elderly patients with dementia is often challenging. We describe performing palliative surface mold brachytherapy (SMBT) in an elderly patient with advanced dementia for pain control using music therapy to assist with agitation. Case Description: The patient was a 97-year-old Japanese woman with advanced dementia. Exudate was observed from her tumor, and she complained of Grade 2 severity pain using Support team assessment schedule (STAS), especially when undergoing would dressings. Given her advanced dementia, she was not considered a candidate for radical surgery or external beam radiotherapy. We instead treated her with high-dose-rate (HDR) SMBT. Due to her advanced dementia associated with agitation, she could not maintain her position. She was able to remain calm while listening to traditional Japanese enka music, which enables our team to complete her radiation without using anesthetics or sedating analgesics. Her localized pain severity decreased ≤21 days and the exudate fluid disappeared ≤63 days after HDR-SMBT. Her tumor was locally controlled until her death from intercurrent disease 1 year after HDR-SMBT. Discussion: Single fraction palliative HDR-SMBT was useful for successful treatment of skin cancer in an elderly patient. Traditional Japanese music helped reduce her agitation to complete HDR-SMBT. For elderly patients with agitation associated with dementia, we should consider using music and music therapy to facilitate radiation therapy.

Perioperative renal function change and oncological outcomes of radical nephroureterectomy in patients with upper tract urothelial carcinoma: A multicenter retrospective study.

BACKGROUND: The effect of radical nephroureterectomy (RNUx) on postoperative renal function in patients diagnosed with upper tract urothelial carcinoma (UTUC) has not been thoroughly explored. METHODS: We conducted a retrospective analysis including 785 patients who underwent RNUx for UTUC. We assessed the preoperative and postoperative estimated glomerular filtration rates (eGFRs) and factors related to the decline in eGFR. Additionally, we examined the effect of comorbidities (diabetes or hypertension) on the postoperative eGFR at 1 year. Cox proportional hazard models were employed to investigate the clinical effect of RNUx on oncological outcomes, including non-urothelial tract recurrence-free survival (NUTRFS), cancer-specific survival (CSS), and overall survival (OS). RESULTS: The median preoperative and postoperative eGFR levels were 54.7 and 40.6 ml/min/1.73 m2 respectively. The proportions of patients with preoperative and postoperative eGFR ≥60 mL/min/1.73 m2 were 35.9% and 5.1%, respectively. The median decline in the eGFR after surgery was 26.8%. Patients with preoperative eGFR <60 ml/min/1.73 m2 demonstrated significantly lower odds of a postoperative decline in eGFR of 25% or more. The effect of comorbidities on postoperative eGFR at 1 year was significant (P = 0.048). The 3-year NUTRFS, CSS, and OS rates were 72.9%, 85.2%, and 81.5%, respectively. Preoperative chronic kidney disease was an independent factor associated with inferior NUTRFS, CSS, and OS. CONCLUSION: Different degrees of impairment of renal function occur among UTUC patients. Only 5.1% of patients retain a postoperative eGFR ≥60 ml/min/1.73 m2. Preoperative renal impairment was linked to reduced odds of postoperative eGFR decrease and associated with survival. In addition, the presence of comorbidities had a significant effect on the decline in eGFR. These findings emphasize the importance of developing evidence-based perioperative treatment strategies for UTUC patients with impaired renal function.

Effective optimization strategy for large optimization volume object, remaining volume at risk (RVR):α-value selection and usage from generalized equivalent uniform dose (gEUD) curve deviation perspective.

Objective.A large optimization volume for intensity-modulated radiation therapy (IMRT), such as the remaining volume at risk (RVR), is traditionally unsuitable for dose-volume constraint control and requires planner-specific empirical considerations owing to the patient-specific shape. To enable less empirical optimization, the generalized equivalent uniform dose (gEUD) optimization is effective; however, the utilization of parametera-values remains elusive. Our study clarifies thea-value characteristics for optimization and to enable effectivea-value use.Approach.The gEUD can be obtained as a function of itsa-value, which is the weighted generalized mean; its curve has a continuous, differentiable, and sigmoid shape, deforming in its optimization state with retained curve characteristics. Using differential geometry, the gEUD curve changes in optimization is considered a geodesic deviation intervened by the forces between deforming and retaining the curve. The curvature and gradient of the curve are radically related to optimization. The vertex point (a=ak) was set and thea-value roles were classified into the following three parts of the curve with respect to thea-value: (i) high gradient and middle curvature, (ii) middle gradient and high curvature, and (iii) low gradient and low curvature. Then, a strategy for multiplea-values was then identified using RVR optimization.Main results.Eleven head and neck patients who underwent static seven-field IMRT were used to verify thea-value characteristics and curvature effect for optimization. The lowera-value (i) (a= 1-3) optimization was effective for the whole dose-volume range; in contrast, the effect of highera-value (iii) (a= 12-20) optimization addressed strongly the high-dose range of the dose volume. The middlea-value (ii) (arounda=ak) showed intermediate but effective high-to-low dose reduction. Thesea-value characteristics were observed as superimpositions in the optimization. Thus, multiple gEUD-based optimization was significantly superior to the exponential constraints normally applied to the RVR that surrounds the PTV, normal tissue objective (NTO), resulting in up to 25.9% and 8.1% improvement in dose-volume indices D2% and V10Gy, respectively.Significance.This study revealed an appropriatea-value for gEUD optimization, leading to favorable dose-volume optimization for the RVR region using fixed multiplea-value conditions, despite the very large and patient-specific shape of the region.

Extracting the gradient component of the gamma index using the Lie derivative method.

Objective. The gamma index (γ) has been extensively investigated in the medical physics and applied in clinical practice. However,γhas a significant limitation when used to evaluate the dose-gradient region, leading to inconveniences, particularly in stereotactic radiotherapy (SRT). This study proposes a novel evaluation method combined withγto extract clinically problematic dose-gradient regions caused by irradiation including certain errors.Approach. A flow-vector field in the dose distribution is obtained when the dose is considered a scalar potential. Using the Lie derivative from differential geometry, we definedL,S, andUto evaluate the intensity, vorticity, and flow amount of deviation between two dose distributions, respectively. These metrics multiplied byγ(γL,γS,γU), along with the threshold valueσ, were verified in the ideal SRT case and in a clinical case of irradiation near the brainstem region using radiochromic films. Moreover, Moran's gradient index (MGI), Bakai's χ factor, and the structural similarity index (SSIM) were investigated for comparisons.Main results. A highL-metric value mainly extracted high-dose-gradient induced deviations, which was supported by highSandUmetrics observed as a robust deviation and an influence of the dose-gradient, respectively. TheS-metric also denotes the measured similarity between the compared dose distributions. In theγdistribution,γLsensitively detected the dose-gradient region in the film measurement, despite the presence of noise. The thresholdσsuccessfully extracted the gradient-error region whereγ> 1 analysis underestimated, andσ= 0.1 (plan) andσ= 0.001 (film measurement) were obtained according to the compared resolutions. However, the MGI, χ, and SSIM failed to detect the clinically interested region.Significance. Although further studies are required to clarify the error details, this study demonstrated that the Lie derivative method provided a novel perspective for the identifying gradient-induced error regions and enabled enhanced and clinically significant evaluations ofγ.

Patient-specific three-dimensional dose distribution prediction via deep learning for prostate cancer therapy: Improvement with the structure loss.

PURPOSE: Deep learning (DL)-based dose distribution prediction can potentially reduce the cost of inverse planning process. We developed and introduced a structure-focused loss (Lstruct) for 3D dose prediction to improve prediction accuracy. This study investigated the influence of Lstruct on DL-based dose prediction for patients with prostate cancer. The proposed Lstruct, which is similar in concept to dose-volume histogram (DVH)-based optimization in clinical practice, has the potential to provide more interpretable and accurate DL-based optimization. METHODS: This study involved 104 patients who underwent prostate radiotherapy. We used 3D U-Net-based architecture to predict dose distributions from computed tomography and contours of the planning target volume and organs-at-risk. We trained two models using different loss functions: L2 loss and Lstruct. Predicted doses were compared in terms of dose-volume parameters and the Dice similarity coefficient of isodose volume. RESULTS: DVH analysis showed that the Lstruct model had smaller errors from the ground truth than the L2 model. The Lstruct model achieved more consistent dose distributions than the L2 model, with errors close to zero. The isodose Dice score of the Lstruct model was greater than that of the L2 model by >20% of the prescribed dose. CONCLUSIONS: We developed Lstruct using labels of inputted contours for DL-based dose prediction for prostate radiotherapy. Lstruct can be generalized to any DL architecture, thereby enhancing the dose prediction accuracy.

Clinical target volume segmentation based on gross tumor volume using deep learning for head and neck cancer treatment.

Accurate clinical target volume (CTV) delineation is important for head and neck intensity-modulated radiation therapy. However, delineation is time-consuming and susceptible to interobserver variability (IOV). Based on a manual contouring process commonly used in clinical practice, we developed a deep learning (DL)-based method to delineate a low-risk CTV with computed tomography (CT) and gross tumor volume (GTV) input and compared it with a CT-only input. A total of 310 patients with oropharynx cancer were randomly divided into the training set (250) and test set (60). The low-risk CTV and primary GTV contours were used to generate label data for the input and ground truth. A 3D U-Net with a two-channel input of CT and GTV (U-NetGTV) was proposed and its performance was compared with a U-Net with only CT input (U-NetCT). The Dice similarity coefficient (DSC) and average Hausdorff distance (AHD) were evaluated. The time required to predict the CTV was 0.86 s per patient. U-NetGTV showed a significantly higher mean DSC value than U-NetCT (0.80 ± 0.03 and 0.76 ± 0.05) and a significantly lower mean AHD value (3.0 ± 0.5 mm vs 3.5 ± 0.7 mm). Compared to the existing DL method with only CT input, the proposed GTV-based segmentation using DL showed a more precise low-risk CTV segmentation for head and neck cancer. Our findings suggest that the proposed method could reduce the contouring time of a low-risk CTV, allowing the standardization of target delineations for head and neck cancer.

Artificial intelligence-aided lytic spinal bone metastasis classification on CT scans.

PURPOSE: Spinal bone metastases directly affect quality of life, and patients with lytic-dominant lesions are at high risk for neurological symptoms and fractures. To detect and classify lytic spinal bone metastasis using routine computed tomography (CT) scans, we developed a deep learning (DL)-based computer-aided detection (CAD) system. METHODS: We retrospectively analyzed 2125 diagnostic and radiotherapeutic CT images of 79 patients. Images annotated as tumor (positive) or not (negative) were randomized into training (1782 images) and test (343 images) datasets. YOLOv5m architecture was used to detect vertebra on whole CT scans. InceptionV3 architecture with the transfer-learning technique was used to classify the presence/absence of lytic lesions on CT images showing the presence of vertebra. The DL models were evaluated via fivefold cross-validation. For vertebra detection, bounding box accuracy was estimated using intersection over union (IoU). We evaluated the area under the curve (AUC) of a receiver operating characteristic curve to classify lesions. Moreover, we determined the accuracy, precision, recall, and F1 score. We used the gradient-weighted class activation mapping (Grad-CAM) technique for visual interpretation. RESULTS: The computation time was 0.44 s per image. The average IoU value of the predicted vertebra was 0.923 ± 0.052 (0.684-1.000) for test datasets. In the binary classification task, the accuracy, precision, recall, F1-score, and AUC value for test datasets were 0.872, 0.948, 0.741, 0.832, and 0.941, respectively. Heat maps constructed using the Grad-CAM technique were consistent with the location of lytic lesions. CONCLUSION: Our artificial intelligence-aided CAD system using two DL models could rapidly identify vertebra bone from whole CT images and detect lytic spinal bone metastasis, although further evaluation of diagnostic accuracy is required with a larger sample size.

Feasibility of Novel Technique of Flexible Cystoscopic En Bloc Snare Resection of Bladder Tumor: f-ESRBT.

Background: En bloc resection of bladder tumors (ERBT) has been used as a treatment option to improve pathologic diagnostic accuracy in non-muscle invasive bladder cancer. We report on the feasibility of a novel ERBT technique using an electrosurgical snare with flexible cystoscope: flexible cystoscopic En bloc Snare Resection of Bladder Tumor (f-ESRBT). Methods: We used the electrosurgical snare to resect a superficial bladder tumor after injection of 50% glucose in the submucosa at the tumor base. We collected each resected tumor with a basket catheter and coagulated the resected area with a coagulation electrode. A flexible cystoscope was used for all procedures. Results/Discussion: We performed 10 operations. Mean tumor size was 10.2 ± 7.3 mm and mean surgery time was 13.8 ± 6.8 minutes. All procedures were performed without complications. Results showed f-ESRBT to be simple and minimally invasive and to enable accurate pathologic diagnoses. Conclusion: f-ESRBT is a feasible treatment option for small and non-muscle invasive bladder cancer.

Deep learning-based detection of patients with bone metastasis from Japanese radiology reports.

PURPOSE: Deep learning (DL) is a state-of-the-art technique for developing artificial intelligence in various domains and it improves the performance of natural language processing (NLP). Therefore, we aimed to develop a DL-based NLP model that classifies the status of bone metastasis (BM) in radiology reports to detect patients with BM. MATERIALS AND METHODS: The DL-based NLP model was developed by training long short-term memory using 1,749 free-text radiology reports written in Japanese. We adopted five-fold cross-validation and used 200 reports for testing the five models. The accuracy, sensitivity, specificity, precision, and area under the receiver operating characteristics curve (AUROC) were used for the model evaluation. RESULTS: The developed model demonstrated classification performance with mean ± standard deviation of 0.912 ± 0.012, 0.924 ± 0.029, 0.901 ± 0.014, 0.898 ± 0.012, and 0.968 ± 0.004 for accuracy, sensitivity, specificity, precision, and AUROC, respectively. CONCLUSION: The proposed DL-based NLP model may help in the early and efficient detection of patients with BM.

Comparison of dosimetric parameters and robustness for rotational errors in fractionated stereotactic irradiation using automated noncoplanar volumetric modulated arc therapy for patients with brain metastases: single- versus multi-isocentric technique.

To compare the dosimetric parameters of automated noncoplanar volumetric modulated arc therapy plans using single-isocentric (SIC) and multi-isocentric (MIC) techniques for patients with two brain metastases (BMs) in stereotactic irradiation and to evaluate the robustness of rotational errors. The SIC and MIC plans were retrospectively generated (35 Gy/five fractions) for 58 patients. Subsequently, a receiver operating characteristic curve analysis between the tumor surface distance (TSD) and V25Gy was performed to determine the thresholds for the brain tissue. The SIC and MIC plans were recalculated based on the rotational images to evaluate the dosimetric impact of rotational error. The MIC plans showed better brain tissue sparing for TSD > 6.6 cm. The SIC plans provided a significantly better conformity index for TSD ≤ 6.6 cm, while significantly lower gradient index was obtained (3.22 ± 0.56vs. 3.30 ± 0.57, p < 0.05) in the MIC plans with TSD > 6.6 cm. For organs at risk (OARs) (brainstem, chiasm, lens, optic nerves, and retinas), D0.1 cc was significantly lower (p < 0.05) in the MIC plans than in the SIC plans. The prescription dose could be delivered (D99%) to the gross tumor volume (GTV) for patients with TSD ≤ 6.6 cm when the rotational error was < 1°, whereas 31% of the D99% of GTV fell below the prescription dose with TSD > 6.6 cm. MIC plans can be an optimal approach for reducing doses to OARs and providing robustness against rotational errors in BMs with TSD > 6.6 cm.

Evaluation of Stopping Power Ratio Calculation Using Dual-energy Computed Tomography With Fast Kilovoltage Switching for Treatment Planning of Particle Therapy.

BACKGROUND/AIM: This study evaluated the calculation accuracy of the stopping power ratio (SPR) using dual-energy computed tomography with fast kilovoltage switching (FKSCT) for particle therapy. MATERIALS AND METHODS: A tissue characterization phantom with various reference materials was scanned to obtain single-energy computed tomography (SECT) images and generate virtual monochromatic images at 77 keV (VMI77keV) and 140 keV (VMI140keV), water density (WD) images, and effective Z (Zeff) images. For SECT, VMI77keV and VMI140keV lookup tables were generated to convert the measured Hounsfield value into the theoretical SPR for a normal phantom size. Subsequently, the reference materials were scanned in small and large phantoms. The SPR was calculated using the lookup tables of SECT (SPRSECT) images, VMI77keV (SPR77keV), and VMI140keV (SPR140keV), and it was derived from the WD and Zeff (SPRWD). RESULTS: In the normal-sized phantom, the overall mean difference between SPRWD and theoretical SPR was -0.3%, and remained below 2% for most reference materials. For the large phantom, the overall mean absolute difference for SPR140keV (3.0%, p=0.006) and SPRWD (3.2%, p=0.002) for the reference materials was significantly lower than that for SPRSECT (5.9%). For the small phantom, a significant reduction in the mean difference in the SPR calculation was observed in SPR77keV (1.0%, p=0.001) and SPR140keV (1.1%, p=0.013) compared with SPRSECT (2.2%). CONCLUSION: VMI140keV generated using FKSCT significantly improves the estimation accuracy of SPR compared with SECT. Thus, FKSCT may be used to improve the dose calculation accuracy for treatment planning of particle therapy.