Radiomics model to classify mammary masses using breast DCE-MRI compared to the BI-RADS classification performance.

BACKGROUND: Recent advanced in radiomics analysis could help to identify breast cancer among benign mammary masses. The aim was to create a radiomics signature using breast DCE-MRI extracted features to classify tumors and to compare the performances with the BI-RADS classification. MATERIAL AND METHODS: From September 2017 to December 2019 images, exams and records from consecutive patients with mammary masses on breast DCE-MRI and available histology from one center were retrospectively reviewed (79 patients, 97 masses). Exclusion criterion was malignant uncertainty. The tumors were split in a train-set (70%) and a test-set (30%). From 14 kinetics maps, 89 radiomics features were extracted, for a total of 1246 features per tumor. Feature selection was made using Boruta algorithm, to train a random forest algorithm on the train-set. BI-RADS classification was recorded from two radiologists. RESULTS: Seventy-seven patients were analyzed with 94 tumors, (71 malignant, 23 benign). Over 1246 features, 17 were selected from eight kinetic maps. On the test-set, the model reaches an AUC = 0.94 95 CI [0.85-1.00] and a specificity of 33% 95 CI [10-70]. There were 43/94 (46%) lesions BI-RADS4 (4a = 12/94 (13%); 4b = 9/94 (10%); and 4c = 22/94 (23%)). The BI-RADS score reached an AUC = 0.84 95 CI [0.73-0.95] and a specificity of 17% 95 CI [3-56]. There was no significant difference between the ROC curves for the model or the BI-RADS score (p = 0.19). CONCLUSION: A radiomics signature from features extracted using breast DCE-MRI can reach an AUC of 0.94 on a test-set and could provide as good results as BI-RADS to classify mammary masses.

The uterine volume is dramatically decreased after hematopoietic stem cell transplantation during childhood regardless of the conditioning regimen.

OBJECTIVE: To study the impact of hematopoietic stem cell transplantation (HSCT) on the uterine volume of childhood acute leukemia (AL) survivor depending on age at HSCT and the type of myeloablative conditioning regimen. SETTING: Thirteen French University Teaching Hospitals. DESIGN: Prospective cohort study. PATIENT(S): Eighty-eight women who underwent HSCT during childhood or adolescence for AL compared to a control group. INTERVENTION(S): A multicentric prospective national study compared the uterine volume in a cohort of childhood AL survivor adult women treated with HSCT, matched 1:1 to control women. Pelvic magnetic resonance imaging scans included diffusion-weighted imaging sequences. Scans were centralized for a double-blinded reading by 2 radiologists. MAIN OUTCOME MEASURE(S): Uterine volume, uterine body-to-cervix ratio, and apparent diffusion coefficient. RESULT(S): The mean age at HSCT was 9.1 ± 0.3 years with a mean follow-up duration of 16.4 ± 0.5 years. The cohort of 88 HSCT survivor women was composed of 2 subgroups depending on the myeloablative conditioning regimen received: an alkylating agent-based regimen group (n = 34) and a total body irradiation (TBI)-based regimen group (n = 54). Among the 88 women, 77 were considered as having a "correct hormonal balance" with estrogens supplied by hormone replacement therapy (HRT) for premature ovarian insufficiency (POI) or because of a residual ovarian function. In the control group (n = 88), the mean uterine volume was 79.7 ± 3.3 mL. The uterine volume significantly decreased in all HSCT survivor women. After the alkylating agent-based regimen, the uterine volume was 45.3 ± 5.6 mL, corresponding to a significant volume reduction of 43.1% (28.8-57.4%) compared with that of the control group. After TBI, the uterine volume was 19.6 ± 1.9 mL, corresponding to a significant volume reduction of 75.3% (70.5%-80.2%) compared with that of the control group. After the alkylating agent-based regimen, the uterine volume dramatically decreased in women with POI without HRT compared with that in those with a correct hormonal balance (15.2 ± 2.6 vs. 49.3 ± 6 mL). In contrast, after TBI, the uterine volume was similar in all women, with no positive effect of hormonal impregnation on the uterine volume (16.3 ± 2.6 vs. 20.1 ± 2.2 mL, respectively). CONCLUSION(S): The uterine volume was diminished after HSCT, regardless of the conditioning regimen. The physiopathology needs to be further investigated: specific impact of a high dose of an alkylating agent; impact of hormone deprivation around puberty; poor compliance to HRT; or different myometrial impact of HRT compared with endogenous ovarian estrogens? CLINICAL TRIAL REGISTRATION NUMBER: ClinicalTrials.gov/NCT03583294 (enrollment of the first subject, November 11, 2017; enrollment of the last subject, June 25, 2021).

Cardiac multidetector computed tomography in infective endocarditis: a pictorial essay.

OBJECTIVES: The goals of this pictorial essay are: (1) to set out a multislice computed tomography (MSCT) imaging protocol to assess infective endocarditis (IE); (2) to give an MSCT overview of valvular and peri-valvular involvement during IE; (3) to give a CT overview of septic embolism and infectious pseudoaneurysms during IE. METHODS: MSCT acquisition protocols to assess IE are performed in two different phases: the first acquisition, under electrocardiography (ECG) gating, covers the cardiac structures during first-pass iodine injection; the second acquisition covers the thorax, abdomen, pelvic and cerebral regions. RESULTS: Valvular and peri-valvular lesions during IE are: vegetation-a hypodense, homogeneous, irregular mass on a valve or endocardial structure; perforation-a defect in the leaflet; valvular aneurysm-loss of the homogenous curvature of the leaflet; valvular thickening; peri-valvular abscess; pseudoaneurysm; fistula and disinsertion of a prosthetic valve. Extra-cardiac location could involve all organs. CONCLUSIONS: MSCT can be considered as a useful complement in visualising the cardiac lesions of IE if echocardiography is inconclusive. MSCT is the only imaging modality that provides assessment of valvular and peri-valvular involvement, extra-cardiac lesions, and non-invasive evaluation of the coronary artery anatomy, simultaneously. MAIN MESSAGES: • MSCT provides assessment of coronary anatomy, cardiac and extra-cardiac lesions. • MSCT represents an alternative to echocardiography during IE. • Surgical valve replacement is usually required if vegetation is >10 mm. • Peri-valvular extension (abscesses, pseudoaneurysm and fistulae) required surgical treatment.

Initial metastatic kinetics is the best prognostic indicator in stage IV metastatic melanoma.

AIM: In metastatic melanoma (MM) there is an agreement that a fast or slow progression should influence the choice between drugs with immediate impact (BRAF-inh) or delayed (ipilimumab) activity. MM kinetics thus appears crucial for medical decision, although only estimated through surrogate markers (tumour load or lactate dehydrogenase (LDH)). Our objective was to show that 1-MM kinetics can be measured and 2- is a real prognostic factor. METHOD: Among all stage IV MM, we retrospectively select those with long follow-up who had two comparable total body computed tomography (CT) scans within the first 3 months, and did not receive meantime any treatment with a likely impact on MM kinetics. Kinetics index (KI) was calculated from changes in total metastatic volume (ΔTMV/ΔT). RESULTS: In 126 patients, KI of progression ranges from 0 to 24,839 mm3/day. Overall survival (OS) was significantly much lower in the higher terciles of KI than in the lower ones (median OS of 459, 388 and 183 days, for KI of 0-99, 100-999 and > or =1000 mm3/day, respectively). In the multivariate analysis, KI was more predictive of OS than LDH or tumour load. CONCLUSION: Delaying major treatments in stage IV MM for a few weeks permits a measure of KI, which is the best prognostic indicator in MM. The huge range of KI probably reflects major differences in aggressiveness that any therapeutic decision should take into account. KI could be used to assess prospectively how much the efficacy of each new MM drugs is influenced by MM initial kinetics.