Jean Pierre Tasu

Objectives: To assess the impact of an Artificial Intelligence (AI) limb bone fracture diagnosis software (AIS) on emergency department (ED) workflow and diagnostic accuracy. Materials and Methods: A retrospective study was conducted in two phases—without AIS (Period 1: 1 January 2020–30 June 2020) and with AIS (Period 2: 1 January 2021–30 June 2021). Results: Among 3720 patients (1780 in Period 1; 1940 in Period 2), the discrepancy rate decreased by 17% (p = 0.04) after AIS implementation. Clinically relevant discrepancies showed no significant change (−1.8%, p = 0.99). The mean length of stay in the ED was reduced by 9 min (p = 0.03), and expert consultation rates decreased by 1% (p = 0.38). Conclusions: AIS implementation reduced the overall discrepancy rate and slightly decreased ED length of stay, although its impact on clinically relevant discrepancies remains inconclusive. Key Point: After AI software deployment, the rate of radiographic discrepancies decreased by 17% (p = 0.04) but this was not clinically relevant (−2%, p = 0.99). Length of patient stay in the emergency department decreased by 5% with AI (p = 0.03). Bone fracture AI software is effective, but its effectiveness remains to be demonstrated.

Objectives The aim of the IRECAP study was to evaluate the rate of locally advanced pancreas cancer patients (LAPC) who could undergo R0 or R1 surgery after irreversible electroporation (IRE). Materials and methods IRECAP study is a phase II, single-center, open-label, prospective, non-randomized trial registered at clinicaltrials.gov (NCT03105921). Patients with LAPC were first treated by 3-month neo-adjuvant chemotherapy in order to avoid inclusion of either patients with LAPC having become resectable after chemotherapy or patients with rapid disease progression. In cases of stable disease, IRE was performed percutaneously under CT guidance. Surgery was planned between 28 and 90 days after IRE. Tumor specimens were studied to evaluate the resection margins (R0/R1/R2). Results Six men and 11 women were included (median age 61 years, range 37–77 years). No IRE-related death was observed. Ten patients (58%, 10/17) experienced 25 serious adverse events related to IRE. Four patients progressed between IRE and surgery and were excluded from surgery. Thirteen patients were finally operated, six withheld for pancreas resection, three for diffuse peritoneal carcinosis, two for massive vascular entrapment, and one for hepato-cellular carcinoma not diagnosed before surgery. Rate of R1-R0 was 35% (n = 6/17). Median overall survival was 31 months (95% CI; 4–undefined) for the six patients with R0/R1 resection and 21 months (95% CI; 4–25) for the 11 patients without resection or R2 resection (logrank p = 0.044). Conclusion After neoadjuvant chemotherapy, IRE could provide R0 or R1 resection in 35% of LAPC, which seems to be associated with higher OS. Clinical relevance statement After induction chemotherapy, stable locally advanced pancreatic cancers can be treated by irreversible electroporation, which could lead to a secondary 35% rate of R0 or R1 surgical resection which may be associated with a significantly higher overall survival. Key Points • In cases of unresectable LAPC (locally advanced pancreatic cancer), percutaneous irreversible electroporation (pIRE) is feasible (100% success rate of the procedure), but is associated with a 58% rate of grade 3–4 adverse events. • In patients with unresectable LAPC, pIRE could lead 35% of patients to R0-R1 surgical resection. • From IRE, median overall survival was 31 months (95% CI; 4–undefined) for the patients with R0/R1 resection and 21 months (95% CI; 4–25) for the patients without resection or R2 resection (logrank p = 0.044).

In this paper we investigate the possibility of using needles, which the interventional radiologist inserts near a deep-seated tumor during an electroporation-based therapy, to characterize the electrical conductivity of patient's tissues. Specifically, we propose to exploit voltage/current measurements and imaging that are performed prior to the application of electroporation pulses. The approach is partly based on the concepts of electrical impedance tomography; however, imaging is used to build a specific geometric model and compensate for the lack of information resulting from the small number of electrodes available. 3D canonical and clinical examples, where a few electrodes surround a tumor, demonstrate the feasibility of this method: solving the inverse problem to estimate tissues conductivity converges in a few iterations. For a given error on the measurement, it is also possible to calculate the error on the estimated conductivities. The uncertainty error with clinical data is at best 5% for one of the tissues identified, due to the limitations of the clinical device used. Various improvements to clinical devices are discussed to make the conductivity estimation more accurate but also to extract more information.

Purpose: We aimed to assess the ability of radiomics features extracted from baseline (PET/CT0) and follow-up PET/CT scans, as well as their evolution (delta-radiomics), to predict clinical outcome (durable clinical benefit (DCB), progression, response to therapy, OS and PFS) in non-small cell lung cancer (NSCLC) patients treated with immunotherapy. Methods: 83 NSCLC patients treated with immunotherapy who underwent a baseline PET/CT were retrospectively included. Response was assessed at 6–8 weeks (PET/CT1) using PERCIST criteria and at 3 months with iPERCIST (PET/CT2) or RECIST 1.1 criteria using CT. The predictive performance of clinical parameters (CP), standard PET metrics (SUV, Metabolic Tumor volume, Total Lesion Glycolysis), delta-radiomics and PET and CT radiomics features extracted at baseline and during follow-up were studied. Seven multivariate models with different combinations of CP and radiomics were trained on a subset of patients (75%) using least absolute shrinkage, selection operator (LASSO) and random forest classification with 10-fold cross-validation to predict outcome. Model validation was performed on the remaining patients (25%). Overall and progression-free survival was also performed by Kaplan–Meier survival analysis. Results: Numerous radiomics and delta-radiomics parameters had a high individual predictive value of patient outcome with areas under receiver operating characteristics curves (AUCs) >0.80. Their performance was superior to that of CP and standard PET metrics. Several multivariate models were also promising, especially for the prediction of progression (AUCs of 1 and 0.96 for the training and testing subsets with the PET-CT model (PET/CT0)) or DCB (AUCs of 0.85 and 0.83 with the PET-CT-CP model (PET/CT0)). Conclusions: Delta-radiomics and radiomics features extracted from baseline and follow-up PET/CT images could predict outcome in NSCLC patients treated with immunotherapy and identify patients who would benefit from this new standard. These data reinforce the rationale for the use of advanced image analysis of PET/CT scans to further improve personalized treatment management in advanced NSCLC.