Indeterminate pulmonary nodules in non-rhabdomyosarcoma soft tissue sarcoma: A study of the European paediatric Soft Tissue Sarcoma Study Group.

BACKGROUND: The aim of this study was to assess the clinical impact of indeterminate pulmonary nodules (no more than four pulmonary nodules of less than 5 mm or one nodule measuring between 5 and less than 10 mm by computed tomography [CT]) in children and adolescents with adult-type non-rhabdomyosarcoma soft tissue sarcoma (NRSTS) at diagnosis. METHODS: Patients with NRSTS treated in 11 centers as part of the European paediatric Soft Tissue Sarcoma Study Group (EpSSG) were retrospectively assessed. Local radiologists, blinded to clinical information except for patients' age and tumor histotype, reviewed the chest CT at diagnosis and filled out a case report form. Because patients with or without indeterminate nodules in the EpSSG NRSTS 2005 study received the same type of treatment, event-free survival (EFS) and overall survival (OS) between groups by log-rank test were compared. RESULTS: Overall, 206 patients were examined: 109 (52.9%) were without any nodules, 78 (38%) had at least one indeterminate nodule, and 19 (9.2%) had nodules meeting the definition of metastases, which were then considered to be misclassified and were excluded from further analyses. Five-year EFS was 78.5% (95% CI, 69.4%-85.1%) for patients without nodules and 69.6% (95% CI, 57.9%-78.7%) for patients with indeterminate nodules (p = .135); 5-year OS was 87.4% (95% CI, 79.3%-92.5%) and 79.0% (95% CI, 67.5%-86.8%), respectively (p = .086). CONCLUSIONS: This study suggests that survival does not differ in otherwise nonmetastatic patients with indeterminate pulmonary nodules compared to nonmetastatic patients without pulmonary nodules. PLAIN LANGUAGE SUMMARY: Radiologists should be aware of the classification of indeterminate pulmonary nodules in non-rhabdomyosarcoma soft tissue sarcomas and use it in their reports. More than a third of patients with non-rhabdomyosarcoma soft tissue sarcoma can be affected by indeterminate pulmonary nodules. Indeterminate pulmonary nodules do not significantly affect the overall survival of pediatric patients with non-rhabdomyosarcoma soft tissue sarcoma.

Efficacy and Safety of Adjuvant Radiotherapy in Re-excised Soft-tissue Sarcoma After Unplanned Resection.

INTRODUCTION: The objective of this study was to evaluate the efficacy and safety of adjuvant radiotherapy (aRT) in patients with soft-tissue sarcoma (STS) re-excised after unplanned tumor resection (UPR). MATERIALS AND METHODS: From 2000 to 2015, we retrospectively evaluated patients with STS of limb or trunk who underwent post-UPR re-excision in our expert center and received or not aRT. RESULTS: Median follow-up was 121 months (IQR 94-165). Among the 145 patients, 37 were not treated with aRT (no-RT) and 108 received aRT with a median radiation dose of 50 Gy (IQR 50-60). At 10 years, patients in the aRT and no-RT groups showed a cumulative incidence of local failure (10y-LF) of 14.7% and 37.7%, and a local recurrence-free survival (10y-LRFS) of 61.3% and 45.8%, respectively. Multivariate analysis identified aRT and age ≥70 years as independent predictors of both LF and LRFS, while grade 3 and deep-seated tumor were independent predictors of LRFS. In overall population, 10-year distant metastasis-free survival (10y-DMFS) and overall survival (10y-OS) were 63.7% and 69.4%. In multivariate analyses, age ≥70 years, grade 3, and deep-seated lesion were associated with shorter DMFS and OS. Acute severe adverse events were not significantly increased in aRT group (14.8% vs. 18.1%, P = .85) but dramatically increased if radiation dose exceeded 50 Gy (risk ratio 2.96 compared to ≤50 Gy, P = .04). CONCLUSION: In STS patients re-excised after UPR, 50 Gy aRT was safe and associated with reduced LF and longer LRFS. It seems to be beneficial even in absence of residual disease or in absence of initial adverse prognostic factors.

Prognostic factors of the synovial sarcoma of the extremities: imaging does matter.

OBJECTIVES: Synovial sarcomas (SS) of the extremities are rare soft tissue sarcomas that are more common in young adults. We deciphered the imaging phenotype of SS with the aim to determine if imaging could provide an incremental value to currently known prognostic factors (PF)-age and histological grade-to predict long-term overall survival (OS). METHODS: This retrospective multicenter study included consecutive pediatric and adult patients with synovial sarcomas of the extremities from December 2002 to August 2020. Inclusion criteria were (i) a follow-up greater than 5 years and (ii) available pre-therapeutic MRI. A subset analysis included MRI and CT-scan. Clinical, pathological, and imaging variables were collected in all patients. The primary endpoint was to evaluate the association of these variables with OS using univariate and multivariate Cox regressions. RESULTS: Out of 428 patients screened for eligibility, 98 patients (mean age: 37.1 ± 15.2 years) were included (MRI: n = 98/98, CT scan: n = 34/98; 35%). The median OS was 75.25 months (IQR = 55.50-109.12) and thirty-six patients (n = 36/98;37%) died during follow-up. The recurrence rate was 12.2% (n =12/98). SS lesions were mostly grade 2 (57/98; 58%). On MRI, SS had a mean long-axis diameter of 67.5 ± 38.3 mm. On CT scan, 44% (15/34) were calcified. Grade (hazard ratio [HR] = 2.71; 95%CI = 1.30-5.66; p = 0.008), size of the lesions evaluated on MRI (HR = 1.02; 95% CI = 1.01-1.03; p < 0.001), and calcifications on CT scan (HR = 0.10; 95% CI = 0.02-0.50; p = 0.005) were independent PF of OS. CONCLUSIONS: This study demonstrated that imaging biomarkers can be used to predict long-term outcome in patients with SS. Strikingly, the presence of calcifications on CT scan is associated with favorable outcome and provides an incremental value over existing PF such as age, grade, and size. KEY POINTS: • Beyond its diagnostic value, MRI is a pre-operative prognostic tool in synovial sarcomas of the extremities since the size of the lesion is an important prognostic factor. • Calcifications on CT scans are independently and significantly associated with prolonged overall survival.

Prognostic Factors for Local Recurrence after Cryoablation of Desmoid Tumors.

PURPOSE: To determine the risk factors for local of adult patients treated for desmoid tumors by cryoablation. MATERIALS AND METHODS: Eighty-four patients treated for nonabdominopelvic desmoid tumors by cryoablation from July 2012 to July 2020 were included in a retrospective study. The population was composed of 64 women (76.19%) and 20 men (23.81%), aged from 16 to 75 years (median, 35 years ± 14.25). Each patient underwent preprocedural gadolinium-enhanced magnetic resonance imaging and was followed up to 36 months with the same technique. Clinical features, such as tumor size and previous treatment, epidemiological features, and the technical parameters of cryoablation, were studied. RESULTS: Local relapse was found in 19 (22.62%) of 84 patients. The 12-, 24-, and 36-month progression-free survival rates were 89% (95% confidence interval [CI], 79-94), 74% (95% CI, 60-83), and 68% (95% CI, 53-79), respectively. In univariate analysis, significant prognostic factors associated with local recurrence were non-abdominal wall location (P = .042), debulking strategy (P = .0105), risk of visceral injury (P = .034) or peripheral nerve injury during cryoablation (P = .033), previous radiation therapy (P = .043), and treatment before 2016 (P = .008). In multivariate analysis, abdominal wall tumors displayed the best outcome, whereas the neck and trunk showed a high rate of recurrence (hazard ratio, 7.307 [95% CI, 1.396-38.261]). CONCLUSIONS: The local recurrence of desmoid tumors after cryoablation depends on a number of prognostic factors, in particular, a non-abdominal wall location of the tumor and previous local treatment such as surgery or radiation therapy.

Quantitative diffusion-weighted MRI response assessment in rhabdomyosarcoma: an international retrospective study on behalf of the European paediatric Soft tissue sarcoma Study Group Imaging Committee.

OBJECTIVE: To investigate the feasibility of diffusion-weighted magnetic resonance imaging (DW-MRI) as a predictive imaging marker after neoadjuvant chemotherapy in patients with rhabdomyosarcoma. MATERIAL AND METHODS: We performed a multicenter retrospective study including pediatric, adolescent and young adult patients with rhabdomyosarcoma, Intergroup Rhabdomyosarcoma Study group III/IV, treated according to the European paediatric Soft tissue sarcoma Study Group (EpSSG) RMS2005 or MTS2008 studies. DW-MRI was performed according to institutional protocols. We performed two-dimensional single-slice tumor delineation. Areas of necrosis or hemorrhage were delineated to be excluded in the primary analysis. Mean, median and 5th and 95th apparent diffusion coefficient (ADC) were extracted. RESULTS: Of 134 included patients, 82 had measurable tumor at diagnosis and response and DW-MRI scans of adequate quality and were included in the analysis. Technical heterogeneity in scan acquisition protocols and scanners was observed. Mean ADC at diagnosis was 1.1 (95% confidence interval [CI]: 1.1-1.2) (all ADC expressed in * 10-3 mm2/s), versus 1.6 (1.5-1.6) at response assessment. The 5th percentile ADC was 0.8 (0.7-0.9) at diagnosis and 1.1 (1.0-1.2) at response. Absolute change in mean ADC after neoadjuvant chemotherapy was 0.4 (0.3-0.5). Exploratory analyses for association between ADC and clinical parameters showed a significant difference in mean ADC at diagnosis for alveolar versus embryonal histology. Landmark analysis at nine weeks after the date of diagnosis showed no significant association (hazard ratio 1.3 [0.6-3.2]) between the mean ADC change and event-free survival. CONCLUSION: A significant change in the 5th percentile and the mean ADC after chemotherapy was observed. Strong heterogeneity was identified in DW-MRI acquisition protocols between centers and in individual patients.

Sarcopenia and serum biomarkers of oxidative stress after a 6-month physical activity intervention in women with metastatic breast cancer: results from the ABLE feasibility trial.

PURPOSE: Sarcopenia has been identified as an important prognostic factor for patients with cancer. This study aimed at exploring the potential associations between a 6-month physical activity intervention and muscle characteristics, sarcopenia, oxidative stress and toxicities in patients with metastatic breast cancer. METHODS: Women newly diagnosed with metastatic breast cancer (N = 49) participated in an unsupervised, personalized, 6-month physical activity intervention with activity tracker. Computerized tomography images at the third lumbar vertebra were analysed at baseline, three months and six months to assess sarcopenia (muscle mass index < 40 cm2/m2) and muscle quality (poor if muscle attenuation < 37.8 Hounsfield Units). Oxidative markers included plasma antioxidant enzymes (catalase, glutathione peroxidase and superoxide dismutase activities), prooxidant enzymes (NADPH oxidase and myeloperoxidase activities) and oxidative stress damage markers (advanced oxidation protein products, malondialdehyde (MDA) and DNA oxidation. RESULTS: At baseline 53% (mean age 55 years (SD 10.41)) were sarcopenic and 75% had poor muscle quality. Muscle cross sectional area, skeletal muscle radiodensity, lean body mass remained constant over the six months (p = 0.75, p = 0.07 and p = 0.75 respectively), but differed significantly between sarcopenic and non-sarcopenic patients at baseline and 6-months. Sarcopenic patients at baseline were more likely to have an increase of MDA (p = 0.02) at 6 months. Being sarcopenic during at least one moment during the 6-month study was associated with a higher risk of developing severe toxicities (grade > 2) (p = 0.02). CONCLUSIONS: This study suggests potential benefits of physical activity for maintenance of muscle mass. Sarcopenia can alter many parameters and disturb the pro and antioxidant balance.

Design and methods of a national, multicenter, randomized and controlled trial to assess the efficacy of a physical activity program to improve health-related quality of life and reduce fatigue in women with metastatic breast cancer: ABLE02 trial.

BACKGROUND: Patients with a metastatic breast cancer suffer from a deteriorated health-related quality of life and numerous symptoms such as pain, severe fatigue and a decrease of their physical fitness. As the feasibility of a physical activity program has been demonstrated in this population, ABLE02 aims to assess the efficacy of a 6 month-physical activity program using connected devices to improve health-related quality of life and to reduce fatigue in women with metastatic breast cancer. METHODS: ABLE02 is a prospective, national, multicenter, randomized, controlled and open-label study. A total of 244 patients with a metastatic breast cancer, with at least one positive hormone receptor and a first-line chemotherapy planned, will be randomly assigned (1:1 ratio) to: (i) the intervention arm to receive physical activity recommendations, an activity tracker to wear 24 h a day during the whole intervention (6 months) with at least three weekly walking sessions and quizzes each week on physical activity and nutrition (ii) the control arm to receive physical activity recommendations only. Health-related quality of life will be assessed every 6 weeks and main assessments will be conducted at baseline, M3, M6, M12 and M18 to evaluate the clinical, physical, biological and psychological parameters and survival of participants. All questionnaires will be completed on a dedicated application. DISCUSSION: An activity program based on a smartphone application linked to an activity tracker may help to improve quality of life and reduce fatigue of patients with a metastatic breast cancer. The growth of e-health offers the opportunity to get real-time data as well as improving patient empowerment in order to change long-term behaviors. TRIAL REGISTRATION: NCT number: NCT04354233 .

Cryoneurolysis in Patients with Dorsal Neuropathic Pain Secondary to Tumor Invasion.

PURPOSE: To evaluate the safety and efficacy of cryoneurolysis (CNL) in patients with refractory thoracic neuropathic pain related to tumor invasion. MATERIALS AND METHODS: Between January 2013 and May 2017, this single-center and retrospective study reviewed 27 computed tomography-guided CNLs performed on 26 patients for refractory thoracic neuropathic pain related to tumor invasion. Patients with cognitive impairment were excluded. Pain levels were recorded on a visual analog scale (VAS) before the procedure, on days 1, 7, 14, 28 and at each subsequent follow-up appointment. CNL was clinically successful if the postprocedural VAS decreased by 3 points or more. To determine the duration of clinical success, the end of pain relief was defined as either an increased VAS of 2 or more points, the introduction of a new analgesic treatment, a death with controlled pain, or for lost to follow-up patients, the latest follow-up appointment date with controlled pain. RESULTS: Technical success rate was 96.7% and clinical success rate was 100%. Mean preprocedural pain score was 6.4 ± 1.7 and decreased to 2.4 ± 2.4 at day 1; 1.8 ± 1.7 at day 7 (P < .001); 3.3 ± 2.5 at day 14; 3.4 ± 2.6 at day 28 (P < .05). The median duration of pain relief was 45 days (range 14-70). Two minor complications occurred. CONCLUSIONS: Cryoneurolysis is a safe procedure that significantly decreased pain scores in patients with thoracic neuropathic pain related to tumor invasion, with a median duration of clinical success of 45 days.

Percutaneous Cryoablation of Symptomatic Intramuscular Venous Malformation.

PURPOSE: To evaluate the efficacy and safety of cryoablation for venous malformations. MATERIALS AND METHODS: A total of 12 patients with symptomatic intramuscular venous malformations who underwent percutaneous cryoablation between February 2015 and December 2018 were retrospectively studied. The mean age was 42 y (range, 19-58 y). Pain was reported by 11 patients (92%) and swelling by 1 (8%). Pain was assessed with a visual analog scale (VAS) before and after cryoablation. Lesion size was followed with magnetic resonance (MR) imaging at baseline and at 3-mo follow-up. Median initial VAS score was 7 (range, 0-8), and median initial lesion size was 32.5 mm (range, 11-150 mm). RESULTS: The median VAS score at 3 mo was 0 (range, 0-4), and the median lesion size at 3 mo was 0 mm (range, 0-142 mm). Eleven of 12 patients reported an improvement in their pain. MR imaging control showed a treatment scar with no residual lesion in 5 patients and decreased lesion size in 4. No major complications were reported. One minor hematoma and 1 small myositis were noted as defined by Society of Interventional Radiology criteria. CONCLUSIONS: Percutaneous cryoablation is effective and safe for treatment of symptomatic intramuscular venous malformations, with improvement of symptoms.

Progressive Desmoid Tumor: Radiomics Compared With Conventional Response Criteria for Predicting Progression During Systemic Therapy-A Multicenter Study by the French Sarcoma Group.

OBJECTIVE. The response of desmoid tumors (DTs) to chemotherapy is evaluated with Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST 1.1) in daily practice and clinical trials. MRI shows early change in heterogeneity in responding tumors due to a decrease in cellular area and an increase in fibronecrotic content before dimensional response. Heterogeneity can be quantified with radiomics. Our aim was to develop radiomics-based response criteria and to compare their performances with clinical and radiologic response criteria. MATERIALS AND METHODS. Forty-two patients (median age, 38.2 years) were included in this retrospective multicenter study because they presented with progressive DT and had an MRI examination at baseline, which we refer to as "MRI-0," and an early MRI evaluation performed after the first chemotherapy cycle (mean time after first chemotherapy cycle, 3 months [SD, 28 days]), which we refer to as "MRI-1." After signal intensity normalization, voxel size standardization, discretization, and segmentation of DT volume on fat-suppressed contrast-enhanced T1-weighted imaging, 90 baseline and delta 3D radiomics features were extracted. Using cross-validation and least absolute shrinkage and selection operator-penalized Cox regression, a radiomics score was generated. The performances of models based on the radiomics score, modified Response Evaluation Criteria in Solid Tumors, European Association for the Study of the Liver criteria, Cheson criteria, Choi criteria, and revised Choi criteria from MRI-0 to MRI-1 to predict progression-free survival (PFS, as defined by RECIST 1.1) were assessed with the concordance index. The results were adjusted for performance status, tumor volume, prior chemotherapy, current chemotherapy, and ß-catenin mutation. RESULTS. There were 10 cases of progression. The radiomics score included four variables. A high score indicated a poor prognosis. The radiomics score independently correlated with PFS (adjusted hazard ratio = 5.60, p = 0.003), and none of the usual response criteria independently correlated with PFS. The prognostic model based on the radiomics score had the highest concordance index (0.84; 95% CI, 0.71-0.96). CONCLUSION. Quantifying early changes in heterogeneity through a dedicated radiomics score could improve response evaluation for patients with DT undergoing chemotherapy.

Alveolar soft-part sarcoma: can MRI help discriminating from other soft-tissue tumors? A study of the French sarcoma group.

OBJECTIVES: To investigate the imaging features of alveolar soft-part sarcomas (ASPS) on pre-treatment MRI in order to identify relevant criteria to distinguish ASPS from other soft-tissue tumors. METHODS: A series of 25 patients (mean age, 18.5 years old) with histologically proven ASPS from five French comprehensive cancer centers was compared to a control cohort of 292 patients with various histologically proven benign and malignant soft-tissue tumors representative of the 10-year long activity of one center. All had a baseline MRI with contrast-agent administration. Two radiologists independently reviewed the MRIs. Features assessing location, size, signal, architecture, periphery, and vascularization were reported. Their association with the histological diagnosis of ASPS was evaluated with chi-square or Fisher's test. Their prevalence, sensitivity, specificity, odds ratio, and reproducibility were calculated. RESULTS: Eight MRI features were significantly associated with ASPS: deep location (p < 0.001), high signal intensities on T1-weighted imaging (p < 0.001), central area of necrosis (p = 0.001), absence of fibrotic component (p = 0.003), infiltrative growth pattern (p = 0.003), absence of tail sign (p = 0.001), presence of intra- and peritumoral flow-voids (p < 0.001), and number of flow-voids ≥ 5 (p < 0.001). Twenty out of the 25 (80%) ASPS showed at least 7 of these 8 features compared to only four out of 292 (1.4%) tumors of the control cohort (1 benign vascular tumor, 1 solitary fibrous tumor, 2 high-grade soft-tissue sarcomas). The five ASPS with less than 7 out of 8 features measured less than 40 mm. CONCLUSION: The striking histological uniformity of ASPS translates into imaging. However, ASPS may be misdiagnosed as benign tumors or pseudo-tumors, notably intramuscular benign vascular tumors or vascular malformations. KEY POINTS: • ASPS are rare aggressive mesenchymal tumors displaying recurrent MRI features highly reminiscent of the diagnosis. • Deep-seated tumors presenting with mainly high signal intensity on T1-weighted imaging, an absence of fibrotic component, ill-defined margins without aponeurotic extension, and more than five central and peripheral flow-voids are very likely to be ASPS. • ASPS may be misdiagnosed as intramuscular benign vascular tumor or vascular malformation, which occur in the same age group.

A Rare Atypical Intrapericardial Prostate Adenocarcinoma Metastasis With 68Ga-PSMA-11 PET/CT.

ABSTRACT: We report the case of an 88-year-old man recently diagnosed with prostate cancer. The patient underwent a 68Ga-prostate-specific membrane antigen-11 PET/CT for staging assessment. This examination revealed intense and expected uptake in the primary prostate cancer, widespread metastatic involvement including typical adenopathy and bone metastasis, and a less common pulmonary lymphangitic carcinomatosis. Most notably, we discovered a rare intrapericardial metastasis, which is an atypical site for metastasis in general and particularly for prostate adenocarcinoma.

Development of a Secure Web-Based Medical Imaging Analysis Platform: The AWESOMME Project.

Precision medicine research benefits from machine learning in the creation of robust models adapted to the processing of patient data. This applies both to pathology identification in images, i.e., annotation or segmentation, and to computer-aided diagnostic for classification or prediction. It comes with the strong need to exploit and visualize large volumes of images and associated medical data. The work carried out in this paper follows on from a main case study piloted in a cancer center. It proposes an analysis pipeline for patients with osteosarcoma through segmentation, feature extraction and application of a deep learning model to predict response to treatment. The main aim of the AWESOMME project is to leverage this work and implement the pipeline on an easy-to-access, secure web platform. The proposed WEB application is based on a three-component architecture: a data server, a heavy computation and authentication server and a medical imaging web-framework with a user interface. These existing components have been enhanced to meet the needs of security and traceability for the continuous production of expert data. It innovates by covering all steps of medical imaging processing (visualization and segmentation, feature extraction and aided diagnostic) and enables the test and use of machine learning models. The infrastructure is operational, deployed in internal production and is currently being installed in the hospital environment. The extension of the case study and user feedback enabled us to fine-tune functionalities and proved that AWESOMME is a modular solution capable to analyze medical data and share research algorithms with in-house clinicians.

Characterization of Breast Tumors from MR Images Using Radiomics and Machine Learning Approaches.

Determining histological subtypes, such as invasive ductal and invasive lobular carcinomas (IDCs and ILCs) and immunohistochemical markers, such as estrogen response (ER), progesterone response (PR), and the HER2 protein status is important in planning breast cancer treatment. MRI-based radiomic analysis is emerging as a non-invasive substitute for biopsy to determine these signatures. We explore the effectiveness of radiomics-based and CNN (convolutional neural network)-based classification models to this end. T1-weighted dynamic contrast-enhanced, contrast-subtracted T1, and T2-weighted MR images of 429 breast cancer tumors from 323 patients are used. Various combinations of input data and classification schemes are applied for ER+ vs. ER-, PR+ vs. PR-, HER2+ vs. HER2-, and IDC vs. ILC classification tasks. The best results were obtained for the ER+ vs. ER- and IDC vs. ILC classification tasks, with their respective AUCs reaching 0.78 and 0.73 on test data. The results with multi-contrast input data were generally better than the mono-contrast alone. The radiomics and CNN-based approaches generally exhibited comparable results. ER and IDC/ILC classification results were promising. PR and HER2 classifications need further investigation through a larger dataset. Better results by using multi-contrast data might indicate that multi-parametric quantitative MRI could be used to achieve more reliable classifiers.

Epiphyseal-sparing biological reconstruction of bone sarcoma in children: Focus on articular function and growth.

INTRODUCTION: Epiphyseal preservation surgery and biological reconstruction after resection of metaphyseal bone sarcoma in children is a surgical challenge which can only be justified if future joint function is maintained. HYPOTHESIS: The main hypothesis of this work was that long-term function was maintained. The secondary hypotheses were that local control of the disease and growth restoration were achieved, at the cost of an acceptable number of complications. MATERIAL AND METHOD: This was a retrospective study of 14 children with a median age of 8 years [2-14] at the time of surgery. The tumors (Ewing's sarcoma or osteosarcoma) were mostly situated at the knee (n=9) and hip (n=3). The reconstruction used an induced membrane (n=7) or an allograft (n=7). We studied joint function, mechanisms contributing to loss of growth, surgical complications and survival at the last follow-up. RESULTS: At the median follow-up of 76 months [24-130], 9 out of 14 patients required revision for non-union, and 4 of them required a second revision. At the last follow-up, 82% of the length had been restored, due to 3 bone lengthenings and 7 contralateral epiphysiodeses. Preserved joint function was excellent with an average modified MSTS score of 28.3/30 [24-30]. No local recurrence was reported. DISCUSSION: Our experience of epiphyseal preservation allows local control of the disease and very good function but at the cost of a cumbersome surgical program (12 out of 14 patients were reoperated on, with an average of 1.2 interventions per patient). The main difficulty is the growth management, most often by complex programs of alternating bone lengthening and shortening. LEVEL OF EVIDENCE: IV, retrospective study.

Small-Cell Lung Cancer Transformation as a Mechanism of Resistance to Pralsetinib in RET-Rearranged Lung Adenocarcinoma: A Case Report.

The majority of resistance to Rearranged during transfection (RET)-specific tyrosine kinase inhibitors (TKI) described in RET-rearranged non-small cell lung cancer (NSCLC) patients are driven by RET-independent mechanisms. We provide the first case report of a RET-rearranged lung adenocarcinoma (LUAD) transformation into small-cell lung cancer (SCLC) as a mechanism of acquired resistance to pralsetinib. A 43-year-old patient presented with a RET-rearranged LUAD revealed by pleural effusion. After 14 months of response to pralsetinib, biopsy of a progressive pleural lesion found a phenotypic transformation into SCLC. Molecular analysis identified the same RET fusion and TP53 mutation in both primary adenocarcinoma and recurrence as SCLC. The patient achieved partial response after switch to carboplatin and etoposide chemotherapy and presented with progression disease after 6 months. Histological transformation could be a mechanism of resistance to RET-TKIs and rebiopsy should be considered to adapt subsequent treatment.

Radiomics combined with transcriptomics to predict response to immunotherapy from patients treated with PD-1/PD-L1 inhibitors for advanced NSCLC.

Introduction: In this study, we aim to build radiomics and multiomics models based on transcriptomics and radiomics to predict the response from patients treated with the PD-L1 inhibitor. Materials and methods: One hundred and ninety-five patients treated with PD-1/PD-L1 inhibitors were included. For all patients, 342 radiomic features were extracted from pretreatment computed tomography scans. The training set was built with 110 patients treated at the Léon Bérard Cancer Center. An independent validation cohort was built with the 85 patients treated in Dijon. The two sets were dichotomized into two classes, patients with disease control and those considered non-responders, in order to predict the disease control at 3 months. Various models were trained with different feature selection methods, and different classifiers were evaluated to build the models. In a second exploratory step, we used transcriptomics to enrich the database and develop a multiomic signature of response to immunotherapy in a 54-patient subgroup. Finally, we considered the HOT/COLD status. We first trained a radiomic model to predict the HOT/COLD status and then prototyped a hybrid model integrating radiomics and the HOT/COLD status to predict the response to immunotherapy. Results: Radiomic signature for 3 months' progression-free survival (PFS) classification: The most predictive model had an area under the receiver operating characteristic curve (AUROC) of 0.94 on the training set and 0.65 on the external validation set. This model was obtained with the t-test selection method and with a support vector machine (SVM) classifier. Multiomic signature for PFS classification: The most predictive model had an AUROC of 0.95 on the training set and 0.99 on the validation set. Radiomic model to predict the HOT/COLD status: the most predictive model had an AUROC of 0.93 on the training set and 0.86 on the validation set. HOT/COLD radiomic hybrid model for PFS classification: the most predictive model had an AUROC of 0.93 on the training set and 0.90 on the validation set. Conclusion: In conclusion, radiomics could be used to predict the response to immunotherapy in non-small-cell lung cancer patients. The use of transcriptomics or the HOT/COLD status, together with radiomics, may improve the working of the prediction models.

Automatic deep learning method for third lumbar selection and body composition evaluation on CT scans of cancer patients.

Introduction: The importance of body composition and sarcopenia is well-recognized in cancer patient outcomes and treatment tolerance, yet routine evaluations are rare due to their time-intensive nature. While CT scans provide accurate measurements, they depend on manual processes. We developed and validated a deep learning algorithm to automatically select and segment abdominal muscles [SM], visceral fat [VAT], and subcutaneous fat [SAT] on CT scans. Materials and Methods: A total of 352 CT scans were collected from two cancer centers. The detection of the third lumbar vertebra and three different body tissues (SM, VAT, and SAT) were annotated manually. The 5-fold cross-validation method was used to develop the algorithm and validate its performance on the training cohort. The results were validated on an external, independent group of CT scans. Results: The algorithm for automatic L3 slice selection had a mean absolute error of 4 mm for the internal validation dataset and 5.5 mm for the external validation dataset. The median DICE similarity coefficient for body composition was 0.94 for SM, 0.93 for VAT, and 0.86 for SAT in the internal validation dataset, whereas it was 0.93 for SM, 0.93 for VAT, and 0.85 for SAT in the external validation dataset. There were high correlation scores with sarcopenia metrics in both internal and external validation datasets. Conclusions: Our deep learning algorithm facilitates routine research use and could be integrated into electronic patient records, enhancing care through better monitoring and the incorporation of targeted supportive measures like exercise and nutrition.

Evolution of Patterns of Care and Outcomes in the Real-Life Setting for Patients with Metastatic GIST Treated in Three French Expert Centers over Three Decades.

Gastrointestinal stromal tumors (GIST) are rare mesenchymal tumors characterized by KIT or PDGFRA mutations. Over three decades, significant changes in drug discovery and loco-regional (LR) procedures have impacted treatment strategies. We assessed the evolution of treatment strategies for metastatic GIST patients treated in the three national coordinating centers of NetSarc, the French network of sarcoma referral centers endorsed by the National Institute of Cancers, from 1990 to 2018. The primary objective was to describe the clinical and biological profiles as well as the treatment modalities of patients with metastatic GIST in a real-life setting, including access to clinical trials and LR procedures in the metastatic setting. Secondary objectives were to assess (1) patients' outcome in terms of time to next treatment (TNT) for each line of systemic treatment, (2) patients' overall survival (OS), (3) evolution of patients' treatment modalities and OS according to treatment access: <2002 (pre-imatinib approval), 2002-2006 (pre-sunitinib approval), 2006-2014 (pre-regorafenib approval), post 2014, and (4) the impact of clinical trials and LR procedures on TNT and OS in the metastatic setting. 1038 patients with a diagnosis of GIST made in one of the three participating centers between 1990 and 2018 were included in the national prospective database. Among them, 492 patients presented metastasis, either synchronous or metachronous. The median number of therapy lines in the metastatic setting was 3 (range 0-15). More than half of the patients (55%) participated in a clinical trial during the course of their metastatic disease and half (51%) underwent additional LR procedures on metastatic sites. The median OS in the metastatic setting was 83.4 months (95%CI [72.7; 97.9]). The median TNT was 26.7 months (95%CI [23.4; 32.3]) in first-line, 10.2 months (95%CI [8.6; 11.8]) in second line, 6.7 months (95%CI [5.3; 8.5]) in third line, and 5.5 months (95%CI [4.3; 6.7]) in fourth line, respectively. There was no statistical difference in OS in the metastatic setting between the four therapeutic periods (log rank, p = 0.18). In multivariate analysis, age, AFIP Miettinen classification, mutational status, surgery of the primary tumor, participation in a clinical trial in the first line and LR procedure to metastatic sites were associated with longer TNT in the first line, whereas age, mitotic index, mutational status, surgery of the primary tumor and LR procedure to metastatic sites were associated with longer OS. This real-life study advocates for early reference of metastatic GIST patients to expert centers to orchestrate the best access to future innovative clinical trials together with LR strategies and further improve GIST patients' survival.

Prediction of lipomatous soft tissue malignancy on MRI: comparison between machine learning applied to radiomics and deep learning.

OBJECTIVES: Malignancy of lipomatous soft-tissue tumours diagnosis is suspected on magnetic resonance imaging (MRI) and requires a biopsy. The aim of this study is to compare the performances of MRI radiomic machine learning (ML) analysis with deep learning (DL) to predict malignancy in patients with lipomas oratypical lipomatous tumours. METHODS: Cohort include 145 patients affected by lipomatous soft tissue tumours with histology and fat-suppressed gadolinium contrast-enhanced T1-weighted MRI pulse sequence. Images were collected between 2010 and 2019 over 78 centres with non-uniform protocols (three different magnetic field strengths (1.0, 1.5 and 3.0 T) on 16 MR systems commercialised by four vendors (General Electric, Siemens, Philips, Toshiba)). Two approaches have been compared: (i) ML from radiomic features with and without batch correction; and (ii) DL from images. Performances were assessed using 10 cross-validation folds from a test set and next in external validation data. RESULTS: The best DL model was obtained using ResNet50 (resulting into an area under the curve (AUC) of 0.87 ± 0.11 (95% CI 0.65-1). For ML/radiomics, performances reached AUCs equal to 0.83 ± 0.12 (95% CI 0.59-1) and 0.99 ± 0.02 (95% CI 0.95-1) on test cohort using gradient boosting without and with batch effect correction, respectively. On the external cohort, the AUC of the gradient boosting model was equal to 0.80 and for an optimised decision threshold sensitivity and specificity were equal to 100% and 32% respectively. CONCLUSIONS: In this context of limited observations, batch-effect corrected ML/radiomics approaches outperformed DL-based models.