Automatic gross tumor volume segmentation with failure detection for safe implementation in locally advanced cervical cancer.

Background and Purpose: Automatic segmentation methods have greatly changed the RadioTherapy (RT) workflow, but still need to be extended to target volumes. In this paper, Deep Learning (DL) models were compared for Gross Tumor Volume (GTV) segmentation in locally advanced cervical cancer, and a novel investigation into failure detection was introduced by utilizing radiomic features. Methods and materials: We trained eight DL models (UNet, VNet, SegResNet, SegResNetVAE) for 2D and 3D segmentation. Ensembling individually trained models during cross-validation generated the final segmentation. To detect failures, binary classifiers were trained using radiomic features extracted from segmented GTVs as inputs, aiming to classify contours based on whether their Dice Similarity Coefficient ( DSC ) < T and DSC ⩾ T . Two distinct cohorts of T2-Weighted (T2W) pre-RT MR images captured in 2D sequences were used: one retrospective cohort consisting of 115 LACC patients from 30 scanners, and the other prospective cohort, comprising 51 patients from 7 scanners, used for testing. Results: Segmentation by 2D-SegResNet achieved the best DSC, Surface DSC ( SDSC 3 mm ), and 95th Hausdorff Distance (95HD): DSC = 0.72 ± 0.16, SDSC 3 mm =0.66 ± 0.17, and 95HD = 14.6 ± 9.0 mm without missing segmentation ( M =0) on the test cohort. Failure detection could generate precision ( P = 0.88 ), recall ( R = 0.75 ), F1-score ( F = 0.81 ), and accuracy ( A = 0.86 ) using Logistic Regression (LR) classifier on the test cohort with a threshold T = 0.67 on DSC values. Conclusions: Our study revealed that segmentation accuracy varies slightly among different DL methods, with 2D networks outperforming 3D networks in 2D MRI sequences. Doctors found the time-saving aspect advantageous. The proposed failure detection could guide doctors in sensitive cases.

An MRI Radiomics Approach to Predict the Hypercoagulable Status of Gliomas.

Venous thromboembolic events are frequent complications of Glioblastoma Multiforme (GBM) and low-grade gliomas (LGGs). The overexpression of tissue factor (TF) plays an essential role in the local hypercoagulable phenotype that underlies these complications. Our aim was to build an MRI radiomics model for the non-invasive exploration of the hypercoagulable status of LGG/GBM. Radiogenomics data from The Cancer Genome Atlas (TCGA) and REMBRANDT (Repository for molecular BRAin Neoplasia DaTa) cohorts were used. A logistic regression model (Radscore) was built in order to identify the top 20% TF-expressing tumors, considered to be at high thromboembolic risk. The most contributive MRI radiomics features from LGG/GBM linked to high TF were identified in TCGA using Least Absolute Shrinkage and Selection Operator (LASSO) regression. A logistic regression model was built, whose performance was analyzed with ROC in the TCGA/training and REMBRANDT/validation cohorts: AUC = 0.87 [CI95: 0.81-0.94, p < 0.0001] and AUC = 0.78 [CI95: 0.56-1.00, p = 0.02], respectively. In agreement with the key role of the coagulation cascade in gliomas, LGG patients with a high Radscore had lower overall and disease-free survival. The Radscore was linked to the presence of specific genomic alterations, the composition of the tumor coagulome and the tumor immune infiltrate. Our findings suggest that a non-invasive assessment of the hypercoagulable status of LGG/GBM is possible with MRI radiomics.

Excitement and Concerns of Young Radiation Oncologists over Automatic Segmentation: A French Perspective.

INTRODUCTION: Segmentation of organs at risk (OARs) and target volumes need time and precision but are highly repetitive tasks. Radiation oncology has known tremendous technological advances in recent years, the latest being brought by artificial intelligence (AI). Despite the advantages brought by AI for segmentation, some concerns were raised by academics regarding the impact on young radiation oncologists' training. A survey was thus conducted on young french radiation oncologists (ROs) by the SFjRO (Société Française des jeunes Radiothérapeutes Oncologues). METHODOLOGY: The SFjRO organizes regular webinars focusing on anatomical localization, discussing either segmentation or dosimetry. Completion of the survey was mandatory for registration to a dosimetry webinar dedicated to head and neck (H & N) cancers. The survey was generated in accordance with the CHERRIES guidelines. Quantitative data (e.g., time savings and correction needs) were not measured but determined among the propositions. RESULTS: 117 young ROs from 35 different and mostly academic centers participated. Most centers were either already equipped with such solutions or planning to be equipped in the next two years. AI segmentation software was mostly useful for H & N cases. While for the definition of OARs, participants experienced a significant time gain using AI-proposed delineations, with almost 35% of the participants saving between 50-100% of the segmentation time, time gained for target volumes was significantly lower, with only 8.6% experiencing a 50-100% gain. Contours still needed to be thoroughly checked, especially target volumes for some, and edited. The majority of participants suggested that these tools should be integrated into the training so that future radiation oncologists do not neglect the importance of radioanatomy. Fully aware of this risk, up to one-third of them even suggested that AI tools should be reserved for senior physicians only. CONCLUSIONS: We believe this survey on automatic segmentation to be the first to focus on the perception of young radiation oncologists. Software developers should focus on enhancing the quality of proposed segmentations, while young radiation oncologists should become more acquainted with these tools.

Image-guided adaptive brachytherapy for advanced cervical cancer spreading to the bladder and/or rectum: Clinical outcome and prognostic factors.

INTRODUCTION: Refinements of brachytherapy techniques have led to better local control of locally advanced cervical cancer (LACC), especially with the development of image-guided adaptive brachytherapy (IGABT). Data on the efficacy of brachytherapy in cervical cancer spreading to adjacent organs are scarce. We report the experience of our institution in the treatment of these advanced tumors with IGABT. MATERIALS AND METHODS: Medical records of patients treated for a LACC spreading to the bladder and/or rectum between 2006 and 2020 at Gustave Roussy Institute were analyzed. Dosimetric parameters were collected and converted into 2 Gy per fraction equivalent doses, including the minimal dose received by 90% of the high-risk target volume (D90 CTVHR) and intermediate-risk target volume (D90 CTVIR), as well as the dose received by the most exposed 2 cm3 of the organs at risk. A Cox regression model was used to study the potential associations between clinical and dosimetric factors with survival endpoints and fistula formation. RESULTS AND STATISTICAL ANALYSIS: A total of 81 patients were identified. All patients received pelvic+/- para-aortic radiotherapy, 45 Gy in 25 fractions +/- boost to gross lymph nodes. Concomitant platinum-based chemotherapy was administered in 93.8% of cases. The median D90 CTVHR dose was 75.5 GyEQD2 (SD: 10.39 GyEQD2) and median CTVHR volume was 47.6 cm3 (SD: 27.9 cm3). Median bladder and rectal D2cm3 dose were 75.04 GyEQD2 (SD: 8.72 GyEQD2) and 64.07 GyEQD2 (SD: 6.68 GyEQD2). After a median follow-up of 27.62 ± 25.10 months, recurrence was found in 34/81 patients (42%). Metastatic failure was the most common pattern of relapse (n = 25). Use of a combined interstitial/intracavitary technique and D90 CTVHR ≥ 75.1 GyEQD2 were prognostic factors for OS in univariate analysis (HR = 0.24, 95%IC: 0.057-1, p = 0.023; HR = 0.2, 95%IC: 0.059-0.68, p = 0.0025, respectively). In multivariate analysis, a D90 CTVHR ≥ 75.1 GyEQD2 was significant for OS (HR = 0.23; 95%IC: 0.07, 0.78, p = 0.018). The occurrence of vesicovaginal fistula (VVF) was the most frequent pattern of local recurrence (HR = 4.6, 95%CI: 1.5-14, p = 0.01). CONCLUSION: Advances in brachytherapy modalities improved local control and survival while reducing toxicities. Enhancing local control through dose escalation and combined intracavitary/interstitial brachytherapy techniques is a major factor in patients cure probability, together with systemic intensification to better control distant events.

Radiotherapy of the Primary Disease for Synchronous Metastatic Cancer: A Systematic Review.

In the case of synchronous metastatic disease, the local treatment of primary tumors by radiotherapy has long been reserved for palliative indications. The emergence of the concept of oligometastatic and oligopersistent diseases, the advent of new systemic therapies enabling longer overall survival with an enhanced quality of life, a better understanding of the biologic history of metastatic spread, and technical advances in radiation therapy are revolutionizing the management of patients with de novo metastatic cancer. The prognosis of these patients has been markedly improved and many studies have investigated the survival benefits from the local treatment of various primary tumors in cases of advanced disease at the time of diagnosis or in the case of oligopersistence. This article provides an update on the place of irradiation of the primary tumor in cancer with synchronous metastases, and discusses its interest through published or ongoing trials.

Radiomics to evaluate interlesion heterogeneity and to predict lesion response and patient outcomes using a validated signature of CD8 cells in advanced melanoma patients treated with anti-PD1 immunotherapy.

PURPOSE: While there is still a significant need to identify potential biomarkers that can predict which patients are most likely to respond to immunotherapy treatments, radiomic approaches have shown promising results. The objectives of this study were to evaluate whether a previously validated radiomics signature of CD8 T-cells could predict progressions at a lesion level and whether the spatial heterogeneity of this radiomics score could be used at a patient level to assess the clinical response and survival of melanoma patients. METHODS: Clinical data from patients with advanced melanoma treated in our center with immunotherapy were retrieved. Radiomic features were extracted and the CD8 radiomics signature was applied. A progressive lesion was defined by an increase in lesion size of 20% or more. Dispersion metrics of the radiomics signature were estimated to evaluate the impact of interlesion heterogeneity on patient's response. Fine-tuned cut-offs for predicting overall survival were evaluated after splitting data into training and test sets. RESULTS: A total of 136 patients were included in this study, with 1120 segmented lesions at baseline, and 1052 lesions at first evaluation. A low CD8 radiomics score at baseline was associated with a significantly higher risk of lesion progression (AUC=0.55, p=0.0091), especially for lesions larger than >1 mL (AUC=0.59 overall, p=0.0035, with AUC=0.75, p=0.002 for subcutaneous lesions, AUC=0.68, p=0.01, for liver lesions and AUC=0.62, p=0.03 for nodes). The least infiltrated lesion according to the radiomics score of CD8 T-cells was positively associated with overall survival (training set HR=0.31, p=0.00062, test set HR=0.28, p=0.016), which remained significant in a multivariate analysis including clinical and biological variables. CONCLUSIONS: These results confirm the predictive value at a lesion level of the biologically inspired CD8 radiomics score in melanoma patients treated with anti-PD1-based immunotherapy and may be interesting to assess the disease spatial heterogeneity to evaluate the patient prognosis with potential clinical implication such as tumor selection for focal ablative therapies.

Imaging approaches and radiomics: toward a new era of ultraprecision radioimmunotherapy?

Strong rationale and a growing number of preclinical and clinical studies support combining radiotherapy and immunotherapy to improve patient outcomes. However, several critical questions remain, such as the identification of patients who will benefit from immunotherapy and the identification of the best modalities of treatment to optimize patient response. Imaging biomarkers and radiomics have recently emerged as promising tools for the non-invasive assessment of the whole disease of the patient, allowing comprehensive analysis of the tumor microenvironment, the spatial heterogeneity of the disease and its temporal changes. This review presents the potential applications of medical imaging and the challenges to address, in order to help clinicians choose the optimal modalities of both radiotherapy and immunotherapy, to predict patient's outcomes and to assess response to these promising combinations.

Pulsed Dose Rate Brachytherapy of Lip Carcinoma: Clinical Outcome and Quality of Life Analysis.

PURPOSE: Lip carcinoma represents one of the most common types of head and neck cancer. Brachytherapy is a highly effective therapeutic option for all stages of lip cancers. We report our experience of pulsed dose rate brachytherapy (PDR) as treatment of lip carcinoma. METHODS AND MATERIALS: this retrospective single center study included all consecutive patients treated for a lip PDR brachytherapy in our institution from 2010 to 2019. The toxicities and outcomes of the patients were reported, and a retrospective quality of life assessment was conducted by phone interviews (FACT H&N). RESULTS: From October 2010 to December 2019, 38 patients were treated in our institution for a lip carcinoma by PDR brachytherapy. The median age was 73, and the majority of patients presented T1-T2 tumors (79%). The median total dose was 70.14 Gy (range: 60-85 Gy). With a mean follow-up of 35.4 months, two patients (5.6%) presented local failure, and seven patients (19%) had lymph node progression. The Kaplan-Meier estimated probability of local failure was 7.2% (95% CI: 0.84-1) at two and four years. All patients encountered radiomucitis grade II or higher. The rate of late toxicities was low: three patients (8.3%) had grade II fibrosis, and one patient had grade II chronic pain. All patients would highly recommend the treatment. The median FACT H&N total score was 127 out of 148, and the median FACT H&N Trial Outcome Index was 84. CONCLUSIONS: This study confirms that an excellent local control rate is achieved with PDR brachytherapy as treatment of lip carcinoma, with very limited late side effects and satisfactory functional outcomes. A multimodal approach should help to improve regional control.

Systematic Screening of COVID-19 Disease Based on Chest CT and RT-PCR for Cancer Patients Undergoing Radiation Therapy in a Coronavirus French Hotspot.

PURPOSE: Patients with cancer are presumed to be more vulnerable to COVID-19. We evaluated a screening strategy combining chest computed tomography (CT) and reverse-transcription polymerase chain reaction (RT-PCR) for patients treated with radiation therapy at our cancer center located in a COVID-19 French hotspot during the first wave of the pandemic. METHODS AND MATERIALS: Chest CT images were proposed during radiation therapy CT simulation. Images were reviewed by an expert radiologist according to the COVID-19 Reporting and Data System classification. Nasal swabs with RT-PCR assay were initially proposed in cases of suspicious imaging or clinical context and were eventually integrated into the systematic screening. A dedicated radiation therapy workflow was proposed for COVID-19 patients to limit the risk of contamination. RESULTS: From March 18, 2020 to May 1, 2020, 480 patients were screened by chest CT, and 313 patients had both chest CT and RT-PCR (65%). The cumulative incidence of COVID-19 was 5.4% (95% confidence interval [CI], 3.6-7.8; 26 of 480 patients). Diagnosis of COVID-19 was made before radiation therapy for 22 patients (84.6%) and during RT for 4 patients (15.3%). Chest CT directly aided the diagnosis of 7 cases in which the initial RT-PCR was negative or not feasible, out of a total of 480 patients (1.5%) and 517 chest CT acquisitions. Four patients with COVID-19 at the time of the chest CT screening had a false negative CT. Sensitivity and specificity of chest CT screening in patients with both RT-PCR and chest CT testing were estimated at 0.82 (95% CI, 0.60-0.95) and 0.98 (95% CI, 0.96-0.99), respectively. Adaptation of the radiation therapy treatment was made for all patients, with 7 postponed treatments (median: 5 days; interquartile range, 1.5-14.8). CONCLUSIONS: The benefit of systematic use of chest CT screening during CT simulation for patients undergoing radiation therapy during the COVID-19 pandemic seemed limited.

Dosimetric and volumetric outcomes of combining cyst puncture through an Ommaya reservoir with index-optimized hypofractionated stereotactic radiotherapy in the treatment of craniopharyngioma.

Large cystic craniopharyngioma management combining cyst puncture through an Ommaya reservoir with hypofractionated stereotactic radiotherapy was evaluated. The planning optimization was focused on the gradient and selectivity. Punctured and filled cyst treatment plans were compared with a retrospective analysis of volumetric and functional outcomes.