[18F]FDG PET/CT imaging disproves renal allograft acute rejection in kidney transplant recipients with acute kidney dysfunction: a validation cohort.

PURPOSE: [18F]FDG PET/CT may predict the absence of acute allograft rejection (AR) in kidney transplant recipients (KTRs) with acute kidney injury (AKI). Still, the proposed threshold of 1.6 of the mean of mean standardized uptake values (mSUVmean) in the renal parenchyma needs validation. METHODS: We prospectively performed 86 [18F]FDG PET/CT in 79 adult KTRs who underwent per-cause transplant biopsy for suspected AR. Biopsy-proven polyoma BK nephropathies (n = 7) were excluded. PET/CT was performed 192 ± 18 min after administration of 254.4 ± 30.4 MBq of [18F]FDG. The SUVmean was measured in both upper and lower poles of the renal allograft. One-way analysis of variance (ANOVA) and Tukey's studentized range test were sequentially performed. The receiver operating characteristic (ROC) curve was drawn to discriminate "AR" from non-pathological ("normal" + "borderline") conditions. RESULTS: The median age of the cohort was 55 [43; 63] years, with M/F gender ratio of 47/39. The mean eGFR was 31.9 ± 14.6 ml/min/1.73m2. Biopsies were categorized in 4 groups: "normal" (n = 54), "borderline" (n = 9), "AR" (n = 14), or "others" (n = 2). The median [min; max] mSUVmean reached 1.72 [1.02; 2.07], 1.97 [1.55; 2.11], 2.13 [1.65, 3.12], and 1.84 [1.57; 2.12] in "normal," "borderline," "AR," and "others" groups, respectively. ANOVA demonstrated a significant difference of mSUVmean among groups (F = 13.25, p < 0.0001). The ROC area under the curve was 0.86. Test sensitivity and specificity corresponding to the threshold value of 1.6 were 100% and 30%, respectively. CONCLUSION: [18F]FDG PET/CT may help noninvasively prevent inessential transplant biopsies in KTR with AKI.

[Locally-advanced cervix cancer : multidisciplinary management]. / Cancer du col utérin localement avancé : approche multidisciplinaire.

Cervical cancer is the fourth most common cancer in women and is linked in over 95 % of cases to papillomavirus infection, the incidence of which has fallen in recent years due to screening and vaccination. Almost half of these cancers are diagnosed at a locally advanced stage with an overall 5-year survival of around 65 %. In recent decades, the management strategy of these locally advanced cancers has changed considerably and has allowed the improvement of survival but above all of local control as well as the reduction of toxicity, due to the implementation of imaging. Standard treatment consists of external beam radiation therapy combined with concomitant chemotherapy followed by intrauterine brachytherapy. The role of neo-adjuvant and adjuvant chemotherapy is still being evaluated. New therapeutic approaches (particularly immunotherapy) in addition to standard treatment are also being studied.

Le cancer du col de l'utérus est le quatrième cancer le plus fréquent chez la femme et est lié, dans sup�rieur a 95 % des cas, à une infection par le papillomavirus, dont l'incidence a chuté ces dernières années grâce au dépistage et à la vaccination. Près de la moitié de ces cancers sont diagnostiqués à un stade localement avancé avec une survie globale à 5 ans de l'ordre de 65 %. Ces dernières décennies, la stratégie de prise en charge de ces cancers localement avancés a considérablement changé. Elle a permis l'amélioration de la survie, mais surtout du contrôle local, ainsi que la réduction de la toxicité, grâce notamment à l'implémentation de l'imagerie. Le traitement standard consiste en une radiothérapie externe associée à une chimiothérapie concomitante, suivie d'une curiethérapie intra-utérine. La place de la chimiothérapie néo-adjuvante et adjuvante est toujours en cours d'évaluation. De nouvelles approches thérapeutiques (immunothérapie), en complément du traitement standard, sont aussi à l'étude.

[Chest radiological lesions in COVID-19 : from classical imaging to artificial intelligence]. / Les aspects radiologiques de la pneumopathie à COVID-19 : de l'imagerie conventionnelle à l'intelligence artificielle.

In the course of the pandemic induced by the appearance of a new coronavirus (SARS-CoV-2; COVID-19) causing acute respiratory distress syndrome (ARDS), we had to rethink the diagnostic approach for patients suffering from respiratory symptoms. Indeed, although the use of RT-PCR remains the keystone of the diagnosis, the delay in diagnosis as well as the overload of the microbiological platforms have led us to make almost systematic the use of thoracic imaging for taking in charge of patients. In this context, thoracic imaging has shown a major interest in diagnostic aid in order to better guide the management of patients admitted to hospital. The most common signs encountered are particularly well described in thoracic computed tomography. Typical imaging combines bilateral, predominantly peripheral and posterior, multi-lobar, ground glass opacities. Of note, it is common to identify significant lesions in asymptomatic patients, with imaging sometimes preceding the onset of symptoms. Beyond conventional chest imaging, many teams have developed new artificial intelligence tools to better help clinicians in decision-making.

Dans le décours de la pandémie induite par l'apparition d'un nouveau coronavirus (SARS-CoV-2; COVID-19) à l'origine d'un syndrome de détresse respiratoire aigu (SDRA), nous avons dû repenser l'approche diagnostique des patients souffrant de symptômes respiratoires. En effet, bien que l'usage de la RT-PCR reste la clé de voûte du diagnostic, le retard de diagnostic ainsi que la surcharge des plateformes microbiologiques nous ont menés à rendre quasi systématique l'usage de l'imagerie thoracique pour la prise en charge des patients. L'imagerie thoracique a démontré, dans ce contexte, un intérêt majeur dans l'aide au diagnostic afin d'orienter, au mieux, la prise en charge des patients admis à l'hôpital. Les signes les plus couramment rencontrés sont particulièrement bien décrits en tomodensitométrie thoracique. L'imagerie typique associe des lésions en verre dépoli bilatérales, multi-lobaires, à prédominance périphérique et postérieure. Il est classique d'identifier des lésions significatives chez des patients asymptomatiques, l'imagerie précédant parfois l'apparition de symptômes. Au-delà de l'imagerie thoracique conventionnelle, de nombreuses équipes ont développé de nouveaux outils d'intelligence artificielle afin d'aider, au mieux, les cliniciens dans la prise de décisions.

Fluorodeoxyglucose F(18) Positron Emission Tomography Coupled With Computed Tomography in Suspected Acute Renal Allograft Rejection.

Management of kidney transplant recipients (KTRs) with suspected acute rejection (AR) ultimately relies on kidney biopsy; however, noninvasive tests predicting nonrejection would help avoid unnecessary biopsy. AR involves recruitment of leukocytes avid for fluorodeoxyglucose F(18) ((18) F-FDG), thus (18) F-FDG positron emission tomography (PET) coupled with computed tomography (CT) may noninvasively distinguish nonrejection from AR. From January 2013 to February 2015, we prospectively performed 32 (18) F-FDG PET/CT scans in 31 adult KTRs with suspected AR who underwent transplant biopsy. Biopsies were categorized into four groups: normal (n = 8), borderline (n = 10), AR (n = 8), or other (n = 6, including 3 with polyoma BK nephropathy). Estimated GFR was comparable in all groups. PET/CT was performed 201 ± 18 minutes after administration of 3.2 ± 0.2 MBq/kg of (18) F-FDG, before any immunosuppression change. Mean standard uptake values (SUVs) of both upper and lower renal poles were measured. Mean SUVs reached 1.5 ± 0.2, 1.6 ± 0.3, 2.9 ± 0.8, and 2.2 ± 1.2 for the normal, borderline, AR, and other groups, respectively. One-way analysis of variance demonstrated a significant difference of mean SUVs among groups. A positive correlation between mean SUV and acute composite Banff score was found, with r(2) = 0.49. The area under the receiver operating characteristic curve was 0.93, with 100% sensitivity and 50% specificity using a mean SUV threshold of 1.6. In conclusion, (18) F-FDG PET/CT may help noninvasively prevent avoidable transplant biopsies in KTRs with suspected AR.

Radiotherapy modification based on artificial intelligence and radiomics applied to (18F)-fluorodeoxyglucose positron emission tomography/computed tomography.

Over the last decades, the refinement of radiation therapy techniques has been associated with an increasing interest for individualized radiation therapy with the aim of increasing or maintaining tumor control and reducing radiation toxicity. Developments in artificial intelligence (AI), particularly machine learning and deep learning, in imaging sciences, including nuclear medecine, have led to significant enthusiasm for the concept of "rapid learning health system". AI combined with radiomics applied to (18F)-fluorodeoxyglucose positron emission tomography/computed tomography ([18F]-FDG PET/CT) offers a unique opportunity for the development of predictive models that can help stratify each patient's risk and guide treatment decisions for optimal outcomes and quality of life of patients treated with radiation therapy. Here we present an overview of the current contribution of AI and radiomics-based machine learning models applied to (18F)-FDG PET/CT in the management of cancer treated by radiation therapy.