Treatment Response Assessment for Bladder Cancer on CT Based on Computerized Volume Analysis, World Health Organization Criteria, and RECIST

Deep Learning-Based Detect-Then-Track Pipeline for Treatment Outcome Assessments in Immunotherapy-Treated Liver Cancer

Accurate treatment outcome assessment is crucial in clinical trials. However, due to the image-reading subjectivity, there exist discrepancies among different radiologists. The situation is common in liver cancer due to the complexity of abdominal scans and the heterogeneity of radiological imaging manifestations in liver subtypes. Therefore, we developed a deep learning-based detect-then-track pipeline that can automatically identify liver lesions from 3D CT scans then longitudinally track target lesions, thereby providing the evaluation of RECIST treatment outcomes in liver cancer. We constructed and validated the pipeline on 173 multi-national patients (344 venous-phase CT scans) consisting of a public dataset and two in-house cohorts of 28 centers. The proposed pipeline achieved a mean average precision of 0.806 and 0.726 of lesion detection on the validation and test sets. The model's diameter measurement reliability and consistency are significantly higher than that of clinicians (p = 1.6 × 10-4). The pipeline can make precise lesion tracking with accuracies of 85.7% and 90.8% then finally yield the RECIST accuracies of 82.1% and 81.4% on the validation and test sets. Our proposed pipeline can provide precise and convenient RECIST outcome assessments and has the potential to aid clinicians with more efficient therapeutic decisions.

Using three-dimensional model-based tumour volume change to predict the symptom improvement in patients with renal cell cancer

In our recent study, we explored the efficacy of three-dimensional (3D) measurement of tumor volume in predicting the improvement of quality of life (QoL) in patients suffering from renal cell cancer (RCC), who were treated with axitinib and anti-PD-L1 antibodies. This study encompassed 18 RCC patients, including 10 men and 8 women, with an average age of 56.83 ± 9.94 years. By utilizing 3D Slicer software, we analyzed pre- and post-treatment CT scans to assess changes in tumor volume. Patients' QoL was evaluated through the FKSI-DRS questionnaire. Our findings revealed that 3D models for all patients were successfully created, and there was a moderate agreement between treatment response classifications based on RECIST 1.1 criteria and volumetric analysis (kappa = 0.556, p = 0.001). Notably, nine patients reported a clinically meaningful improvement in QoL following the treatment. Interestingly, the change in tumor volume as indicated by the 3D model showed a higher area under the curve in predicting QoL improvement compared to the change in diameter measured by CT, although this difference was not statistically significant (z = 0.593, p = 0.553). Furthermore, a multivariable analysis identified the change in tumor volume based on the 3D model as an independent predictor of QoL improvement (odds ratio = 1.073, 95% CI 1.002-1.149, p = 0.045).In conclusion, our study suggests that the change in tumor volume measured by a 3D model may be a more effective predictor of symptom improvement in RCC patients than traditional CT-based diameter measurements. This offers a novel approach for assessing treatment response and patient well-being, presenting a significant advancement in the field of RCC treatment.

CSF1 receptor inhibition of tenosynovial giant cell tumor using novel disease-specific MRI measures of tumor burden

Aim: Monitoring treatment of tenosynovial giant cell tumor (TGCT) is complicated by the irregular shape and asymmetrical growth of the tumor. We compared responses to pexidartinib by Response Evaluation Criteria in Solid Tumors (RECIST) 1.1 with those by tumor volume score (TVS) and modified RECIST (m-RECIST). Materials & methods: MRIs acquired every two cycles were assessed centrally using RECIST 1.1, m-RECIST and TVS and tissue damage score (TDS). Results: Thirty-one evaluable TGCT patients were treated with pexidartinib. From baseline to last visit, 94% of patients (29/31) showed a decrease in tumor size (median change: -60% [RECIST], -66% [m-RECIST], -79% [TVS]). All methods showed 100% disease control rate. For TDS, improvements were seen in bone erosion (32%), bone marrow edema (58%) and knee effusion (46%). Conclusion: TVS and m-RECIST offer potentially superior alternatives to conventional RECIST for monitoring disease progression and treatment response in TGCT. TDS adds important information about joint damage associated with TGCT.

Study Progress of Radiomics With Machine Learning for Precision Medicine in Bladder Cancer Management

Bladder cancer is a fatal cancer that happens in the genitourinary tract with quite high morbidity and mortality annually. The high level of recurrence rate ranging from 50 to 80% makes bladder cancer one of the most challenging and costly diseases to manage. Faced with various problems in existing methods, a recently emerging concept for the measurement of imaging biomarkers and extraction of quantitative features called "radiomics" shows great potential in the application of detection, grading, and follow-up management of bladder cancer. Furthermore, machine-learning (ML) algorithms on the basis of "big data" are fueling the powers of radiomics for bladder cancer monitoring in the era of precision medicine. Currently, the usefulness of the novel combination of radiomics and ML has been demonstrated by a large number of successful cases. It possesses outstanding strengths including non-invasiveness, low cost, and high efficiency, which may serve as a revolution to tumor assessment and emancipate workforce. However, for the extensive clinical application in the future, more efforts should be made to break down the limitations caused by technology deficiencies, inherent problems during the process of radiomic analysis, as well as the quality of present studies.

3D Segmentation Algorithms for Computerized Tomographic Imaging: a Systematic Literature Review

This paper presents a systematic literature review concerning 3D segmentation algorithms for computerized tomographic imaging. This analysis covers articles published in the range 2006-March 2018 found in four scientific databases (Science Direct, IEEEXplore, ACM, and PubMed), using the methodology for systematic review proposed by Kitchenham. We present the analyzed segmentation methods categorized according to its application, algorithmic strategy, validation, and use of prior knowledge, as well as its general conceptual description. Additionally, we present a general overview, discussions, and further prospects for the 3D segmentation methods applied for tomographic images.

Association between precystectomy epithelial tumor marker response to neoadjuvant chemotherapy and oncological outcomes in urothelial bladder cancer

INTRODUCTION AND OBJECTIVES

We previously reported that elevated precystectomy serum levels of epithelial tumor markers predict worse oncological outcome in patients with invasive bladder cancer (BC). Herein, we evaluated the effect of neoadjuvant chemotherapy (NAC) on elevated tumor marker levels and their association with oncological outcomes.

METHODS

Under IRB approval, serum levels of Carbohydrate Antigen 125 (CA-125), Carbohydrate Antigen 19-9 (CA 19-9) and Carcinoembryonic Antigen (CEA) were prospectively measured in 480 patients with invasive BC from August 2011 through December 2016. In the subgroup undergoing NAC, markers were measured prior to the first and after the last cycle of chemotherapy (prior to cystectomy).

RESULTS

Three hundred and thirty-seven patients were eligible for the study, with a median age was 71 years (range 34-93) and 81% (272) male. Elevated precystectomy level of any tumor markers (31% of patients) was independently associated with worse recurrence-free survival (hazard ratio [HR] = 2.81; P < 0.001) and overall survival (HR = 3.97; P < 0.001). One hundred and twenty-five (37%) patients underwent NAC, of whom 59 had a complete tumor marker profile and 30 (51%) had an elevated pre-NAC tumor marker. Following completion of chemotherapy, 10/30 (33%) patients normalized their tumor markers, while 20/30 (67%) had one or more persistently elevated markers. There was no difference in clinical or pathological stage between groups (P = 0.54 and P = 0.09, respectively). Further analysis showed a significantly lower rate and longer median time to recurrence/progression in the responder group (50% in responders vs. 90% in nonresponders at a median time of 22 vs. 4.8 months, respectively; P = 0.015). There was also significant difference in mortality rates and median overall survival between the study groups (30% in responders vs. 70% in nonresponders at a median time of 27.3 vs. 11.6 months respectively; P = 0.037). Two of the three patients that died in the normalized tumor marker group had tumor marker relapse at recurrence prior to their death.

CONCLUSIONS

To our knowledge, this is the first study showing tumor marker response to NAC. Patients with persistently elevated markers following NAC have a very poor prognosis following cystectomy, which may help identifying chemotherapy-resistant tumors. A larger, controlled study with longer follow up is needed to determine their role in predicting survival.

Bladder Cancer Segmentation in CT for Treatment Response Assessment: Application of Deep-Learning Convolution Neural Network-A Pilot Study

Assessing the response of bladder cancer to neoadjuvant chemotherapy is crucial for reducing morbidity and increasing quality of life of patients. Changes in tumor volume during treatment is generally used to predict treatment outcome. We are developing a method for bladder cancer segmentation in CT using a pilot data set of 62 cases. 65 000 regions of interests were extracted from pre-treatment CT images to train a deep-learning convolution neural network (DL-CNN) for tumor boundary detection using leave-one-case-out cross-validation. The results were compared to our previous AI-CALS method. For all lesions in the data set, the longest diameter and its perpendicular were measured by two radiologists, and 3D manual segmentation was obtained from one radiologist. The World Health Organization (WHO) criteria and the Response Evaluation Criteria In Solid Tumors (RECIST) were calculated, and the prediction accuracy of complete response to chemotherapy was estimated by the area under the receiver operating characteristic curve (AUC). The AUCs were 0.73 ± 0.06, 0.70 ± 0.07, and 0.70 ± 0.06, respectively, for the volume change calculated using DL-CNN segmentation, the AI-CALS and the manual contours. The differences did not achieve statistical significance. The AUCs using the WHO criteria were 0.63 ± 0.07 and 0.61 ± 0.06, while the AUCs using RECIST were 0.65 ± 007 and 0.63 ± 0.06 for the two radiologists, respectively. Our results indicate that DL-CNN can produce accurate bladder cancer segmentation for calculation of tumor size change in response to treatment. The volume change performed better than the estimations from the WHO criteria and RECIST for the prediction of complete response.

Progress in Fully Automated Abdominal CT Interpretation

OBJECTIVE

Automated analysis of abdominal CT has advanced markedly over just the last few years. Fully automated assessment of organs, lymph nodes, adipose tissue, muscle, bowel, spine, and tumors are some examples where tremendous progress has been made. Computer-aided detection of lesions has also improved dramatically.

CONCLUSION

This article reviews the progress and provides insights into what is in store in the near future for automated analysis for abdominal CT, ultimately leading to fully automated interpretation.