An increasing number of parameters can be considered when making decisions in oncology. Tumor characteristics can also be extracted from imaging through the use of radiomics and add to this wealth of ...clinical data. Machine learning can encompass these parameters and thus enhance clinical decision as well as radiotherapy workflow.
We performed a description of machine learning applications at each step of treatment by radiotherapy in head and neck cancers. We then performed a systematic review on radiomics and machine learning outcome prediction models in head and neck cancers.
Machine Learning has several promising applications in treatment planning with automatic organ at risk delineation improvements and adaptative radiotherapy workflow automation. It may also provide new approaches for Normal Tissue Complication Probability models. Radiomics may provide additional data on tumors for improved machine learning powered predictive models, not only on survival, but also on risk of distant metastasis, in field recurrence, HPV status and extra nodal spread. However, most studies provide preliminary data requiring further validation.
Promising perspectives arise from machine learning applications and radiomics based models, yet further data are necessary for their implementation in daily care.
Concurrent chemoradiotherapy (CRT) with blockade of the PD-1 pathway may enhance immune-mediated tumor control through increased phagocytosis, cell death, and antigen presentation. The NiCOL phase 1 ...trial (NCT03298893) is designed to determine the safety/tolerance profile and the recommended phase-II dose of nivolumab with and following concurrent CRT in 16 women with locally advanced cervical cancer. Secondary endpoints include objective response rate (ORR), progression free survival (PFS), disease free survival, and immune correlates of response. Three patients experience grade 3 dose-limiting toxicities. The pre-specified endpoints are met, and overall response rate is 93.8% 95%CI: 69.8-99.8% with a 2-year PFS of 75% 95% CI: 56.5-99.5%. Compared to patients with progressive disease (PD), progression-free (PF) subjects show a brisker stromal immune infiltrate, higher proximity of tumor-infiltrating CD3
T cells to PD-L1
tumor cells and of FOXP3
T cells to proliferating CD11c
myeloid cells. PF show higher baseline levels of PD-1 and ICOS-L on tumor-infiltrating EMRA CD4
T cells and tumor-associated macrophages, respectively; PD instead, display enhanced PD-L1 expression on TAMs, higher peripheral frequencies of proliferating Tregs at baseline and higher PD-1 levels at week 6 post-treatment initiation on CD4 and CD8 T cell subsets. Concomitant nivolumab plus definitive CRT is safe and associated with encouraging PFS rates. Further validation in the subset of locally advanced cervical cancer displaying pre-existing, adaptive immune activation is warranted.
Lung cancer represents the first cause of cancer-related death in the world. Radiomics studies arise rapidly in this late decade. The aim of this review is to identify important recent publications ...to be synthesized into a comprehensive review of the current status of radiomics in lung cancer at each step of the patients' care.
A literature review was conducted using PubMed/Medline for search of relevant peer-reviewed publications from January 2012 to June 2020.
We identified several studies at each point of patient's care: detection and classification of lung nodules (n=16), determination of histology and genomic (n=10) and finally treatment outcomes predictions (=23). We reported the methodology of those studies and their results and discuss the limitations and the progress to be made for clinical routine applications.
Promising perspectives arise from machine learning applications and radiomics based models in lung cancers, yet further data are necessary for their implementation in daily care. Multicentric collaboration and attention to quality and reproductivity of radiomics studies should be further consider.
Stereotactic radiotherapy (SRT) is gaining increasing importance in metastatic non-small-cell lung cancer (mNSCLC) management. The optimal sequence of tumor irradiation relative to systemic treatment ...remains unclear. If waiting response evaluation to first-line systemic therapy (FLST) before considering local treatment may allow for the exclusion of poorer prognosis progressive tumors that may not benefit from SRT, performing irradiation near immune check point inhibitor (ICI) first administration seems to improve their synergic effect. Herein, we aimed to determine whether delaying SRT after response evaluation to FLST would result in better prognosis. We compared overall survival (OS), progression-free survival (PFS), and time to first subsequent therapy (TFST) for 50 patients locally treated before or within 90 days of initiating FLST (early SRT), with 49 patients treated at least 90 days after initiating FLST (late SRT). Patients treated with conventional chemotherapy alone exhibited significantly poorer median OS, PFS, and TFST in the early SRT arm: (in months) 16.5 8.33-NR vs. 58.3 35.05-NR (p = 0.0015); 4.69 3.57–8.98 vs. 8.20 6.66–12.00 (p = 0.017); and 6.26 4.82–11.8 vs. 10.0 7.44–21.8 (p = 0.0074), respectively. Patient receiving ICI showed no difference in OS (NR 25.2-NR vs. 36.6 35.1-NR, p = 0.79), PFS (7.54 6.23-NR vs. 4.07 2.52-NR, p = 0.19), and TFST (13.7 9.48-NR vs. 10.3 3.54-NR, p = 0.49). These results suggest that delaying SRT treatment in order to filter a rapidly growing tumor may be less necessary when ICI is administered in mNSCLC.
Introduction:
Stereotactic hypofractionated radiotherapy is an effective treatment for brain metastases in oligometastatic patients. Its planning is however time-consuming because of the number of ...organs at risk to be manually segmented. This study evaluates 2 automated segmentation commercial software.
Methods:
Patients were scanned in the treatment position. The computed tomography scan was registered on a magnetic resonance imaging and volumes were manually segmented by a clinician. Then 2 automated segmentations were performed (with iPlan and Smart Segmentation). RT STRUCT files were compared with Aquilab’s Artistruct segment comparison module. We selected common segmented volume ratio as the main judging criterion. Secondary criteria were Dice-Sørensen coefficients, overlap ratio, and additional segmented volume.
Results:
Twenty consecutive patients were included. Agreement between manual and automated contouring was poor. Common segmented volumes ranged from 7.71% to 82.54%, Dice-Sørensen coefficient ranged from 0.0745 to 0.8398, overlap ratio ranged from 0.0414 to 0.7275, and additional segmented volume ranged from 9.80% to 92.25%. Each software outperformed the other on some organs while performing worse on others.
Conclusion:
No software seemed clearly better than the other. Common segmented volumes were much too low for routine use in stereotactic hypofractionated brain radiotherapy. Manual editing is still needed.
Homologous recombination deficiency is a marker of response to poly(ADP-ribose) polymerase inhibitors in different cancer types including ovary, prostate, and pancreatic cancer. To date, no report ...about poly(ADP-ribose) polymerase inhibitors has been published on cervical cancer.
Here we present the case of a patient with cervical cancer treated in this setting. A 49-year-old woman diagnosed with International Federation of Obstetricians and Gynecologists stage 2018 IIIC2 locally advanced undifferentiated cervical cancer received first-line chemoradiotherapy followed by carboplatin, paclitaxel, and bevacizumab with partial response. Because of a family history of cancers, the patient was tested and found positive for a pathogenic BRCA1 germline and somatic mutation, which motivated bevacizumab plus olaparib maintenance treatment. A simple hysterectomy was performed after 2 years stable disease; pathological report showed complete pathological response, and 12 months follow-up showed no recurrence.
Poly(ADP-ribose) polymerase inhibitors could be an alternative maintenance treatment for patients with persistent advanced cervical cancer previously treated with platinum, especially when familial history of cancers is reported. Clinical trials using poly(ADP-ribose) polymerase inhibitors for advanced cervical cancer are warranted.
Area under the curve (AUC) dosing is routinely carried out for carboplatin, but the chosen target AUC values remain largely empirical. This multicenter pharmacokinetic-pharmacodynamic (PK-PD) study ...was performed to determine the covariates involved in the interindividual variability of carboplatin hematotoxicity that should be considered when choosing individual target AUCs.
Three hundred eighty-three patients received carboplatin as part of established regimens. A semi-physiologic population PK-PD model was applied to describe separately the time course of absolute neutrophil and platelet counts using NONMEM software. The plasma ultrafiltrable carboplatin concentration (C(Carbo)) was assumed to inhibit the proliferation of blood cell precursors through a linear model: drug effect = slope × C(Carbo). The slope corresponds to the patients' sensitivity to carboplatin hematotoxicity. The relationships between the patients' sensitivity to the neutropenic or thrombopenic effects of carboplatin and various covariates, including associated chemotherapies, demographic, biologic, and pharmacogenetic data, were studied.
The sensitivity of carboplatin-induced thrombocytopenia decreased in the case of concomitant paclitaxel chemotherapy (slope decreased by 24%), whereas it increased with coadministration of etoposide and gemcitabine (slope increased by 45% and 133%, respectively). For neutropenia, the sensitivity increased when carboplatin was combined with other cytotoxics (slope increased by 76%).
This study provides useful information to clinicians to better estimate the hematopoietic toxicity of carboplatin and thus choose more rationally carboplatin target AUCs as a function of pretreatment or concomitantly administered chemotherapies. For example, an AUC of 5 mg/mL · min is associated with a risk of grade 3 or 4 thrombocytopenia of 2% in combination with paclitaxel versus 38% with gemcitabine in a non-pretreated patient.
Treatment of locally advanced rectal cancer involves chemoradiation, followed by total mesorectum excision. Complete response after chemoradiation is an accurate surrogate for long-term local ...control. Predicting complete response from pre-treatment features could represent a major step towards conservative treatment. Patients with a T2-4 N0-1 rectal adenocarcinoma treated between June 2010 and October 2016 with neo-adjuvant chemoradiation from three academic institutions were included. All clinical and treatment data was integrated in our clinical data warehouse, from which we extracted the features. Radiomics features were extracted from the tumor volume from the treatment planning CT Scan. A Deep Neural Network (DNN) was created to predict complete response, as a methodological proof-of-principle. The results were compared to a baseline Linear Regression model using only the TNM stage as a predictor and a second model created with Support Vector Machine on the same features used in the DNN. Ninety-five patients were included in the final analysis. There were 49 males (52%) and 46 females (48%). Median tumour size was 48 mm (15-130). Twenty-two patients (23%) had pathologic complete response after chemoradiation. One thousand six hundred eighty-three radiomics features were extracted. The DNN predicted complete response with an 80% accuracy, which was better than the Linear Regression model (69.5%) and the SVM model (71.58%). Our model correctly predicted complete response after neo-adjuvant rectal chemoradiotherapy in 80% of the patients of this multicenter cohort. Our results may help to identify patients who would benefit from a conservative treatment, rather than a radical resection.
Introduction
Prostate cancer is the most common cancer in men. Thirty to forty‐seven percent of patients treated with exclusive radiotherapy for prostate cancer will experience intraprostate ...recurrence. The use of radiotherapy in stereotactic conditions allows millimetric accuracy in irradiation to the target zone that minimizes the dose to organs at risk. In this study, we evaluated the clinical outcome of prostatic reirradiation with stereotactic body radiation therapy (SBRT) in patients with intraprostatic recurrence initially treated by radiotherapy.
Method
This single‐center retrospective study included 41 patients diagnosed with exclusive local recurrence of prostate cancer after radiotherapy and treatedby stereotactic Cyberknife irradiation. The objective of this study was to assess the efficacy and the safety of stereotactic reirradiation for patients with intraprostatic recurrence initially treated with radiotherapy.
Results
Median follow‐up was 35 months. The 2‐year biochemical relapse‐free survival was 72.89%, the 2‐year local recurrence free survival was 93.59%, the 2‐year local regional recurrence‐free survival was 85.24%, and the 2‐year metastasis‐free survival was to 91.49%. The analysis of toxicities showed a good tolerance of stereotactic irradiation. Urinary and gastro‐intestinal adverse events was mostly of grades 1–2 (CTCAEv4). Grade 3 toxicity occurred in one to two patients.
Conclusion
Stereotactic reirradiation appears effective and well‐tolerated for local recurrence of prostate cancer and might allow to delay the introduction of hormonal therapy and its side effects.
PDF
