Erratum: On the role of artificial intelligence in medical imaging of COVID-19.

[This corrects the article DOI: 10.1016/j.patter.2021.100269.].

On the role of artificial intelligence in medical imaging of COVID-19.

Although a plethora of research articles on AI methods on COVID-19 medical imaging are published, their clinical value remains unclear. We conducted the largest systematic review of the literature addressing the utility of AI in imaging for COVID-19 patient care. By keyword searches on PubMed and preprint servers throughout 2020, we identified 463 manuscripts and performed a systematic meta-analysis to assess their technical merit and clinical relevance. Our analysis evidences a significant disparity between clinical and AI communities, in the focus on both imaging modalities (AI experts neglected CT and ultrasound, favoring X-ray) and performed tasks (71.9% of AI papers centered on diagnosis). The vast majority of manuscripts were found to be deficient regarding potential use in clinical practice, but 2.7% (n = 12) publications were assigned a high maturity level and are summarized in greater detail. We provide an itemized discussion of the challenges in developing clinically relevant AI solutions with recommendations and remedies.

Outcomes of balloon occlusion in the University of California Morbidly Adherent Placenta Registry.

BACKGROUND: Morbidly adherent placenta, also known as placenta accreta spectrum, is associated with severe maternal morbidity and mortality. Multiple adjunctive procedures have been proposed to improve outcomes, and at many institutions, interventional radiologists will play a role in assisting obstetricians in these cases. OBJECTIVE: The objective of the study was to evaluate the outcomes of women with morbidly adherent placenta who underwent cesarean hysterectomy with aortic balloon occlusion or internal iliac artery balloon occlusion catheters, compared with cesarean hysterectomy with surgical ligation of the iliac arteries, or cesarean hysterectomy without adjunctive procedures. STUDY DESIGN: A retrospective review of women with morbidly adherent placenta treated with cesarean hysterectomy was performed at 5 institutions from May 2014 to April 2018. The balloon occlusion group had either prophylactic aortic or iliac balloons placed prior to cesarean hysterectomy. Comparison groups included those who underwent internal iliac artery ligation prior to hysterectomy or a control group if they underwent cesarean hysterectomy without adjuvant procedures. Evaluated outcomes include estimated blood loss, transfusion requirements, intensive care unit admission, and adverse event rates. RESULTS: There were 171 women with morbidly adherent placenta included in the study. Twenty-eight had balloon placement prior to cesarean hysterectomy, 18 had intraoperative internal iliac artery ligation, and there were 125 control women who underwent cesarean hysterectomy without any adjunctive procedures. Compared with the women who underwent cesarean hysterectomy without adjunctive procedures, women who underwent aortic or iliac artery balloon occlusion prior to hysterectomy had significantly lower estimated blood loss (30.9% decrease, P < .001), transfusion requirements (76.8% decrease, P < .001), intensive care unit admission rates (0% vs 15.2%, P < .001), and intensive care unit stay lengths (0.0 vs 3.1 days, P < .001). Compared with women who underwent surgical ligation of the internal iliac arteries prior to hysterectomy, women who underwent aortic or iliac artery balloon occlusion prior to cesarean hysterectomy had lower estimated blood loss (54.2% decrease, P < .01), transfusion requirements (90.5% decrease, P < .001), operating room times (40.0% decrease, P < .01), intensive care unit admissions rates (0% vs 77.8%, P < .001), intensive care unit stay lengths (0.0 vs 1.4 days, P < .001), and adverse events (3.6% vs 44.4%, P < .01). CONCLUSION: Aortic and iliac artery balloon occlusion are associated with lower estimated blood loss, transfusion requirements, intensive care unit admission rates, and adverse event rates compared with women who underwent internal iliac artery ligation prior to cesarean hysterectomy or women who had no adjunctive interventions prior to cesarean hysterectomy for morbidly adherent placenta.

Uterine Artery Embolization following Cesarean Delivery but prior to Hysterectomy in the Management of Patients with Invasive Placenta.

PURPOSE: To evaluate outcomes of patients with placenta accreta spectrum (PAS) disorders who underwent uterine artery embolization (UAE) following cesarean delivery but before hysterectomy. MATERIALS AND METHODS: A retrospective review of patients with PAS treated with cesarean-hysterectomy (C-hyst) was performed. Patients in the UAE group underwent UAE after cesarean delivery but before hysterectomy; patients in the control group underwent C-hyst alone. Estimated blood loss (EBL), transfusion requirements, length of intensive care unit (ICU) stay, and adverse events were evaluated. RESULTS: The study included 31 patients, 7 in the UAE group and 24 in the control group. Median EBL, transfusion requirements, and length of ICU stay in the UAE group compared with control group were 1,500 mL (range, 500-2,000 mL) vs 2,000 mL (range, 1,000-4,500 mL) (P = .04), 150 mL (range, 0-650 mL) vs 550 mL (range, 0-3,125 mL) (P = .10), and 0 d (range, 0-1 d) vs 0.5 d (range, 0-2 d) (P = .07). All patients in the UAE group had placenta increta; patients in the control group had placenta accreta (29%), increta (54%), and percreta (17%) (P = .10). Subgroup analysis of patients with placenta increta demonstrated that the UAE group had a significant decrease in median EBL (P = .004), transfusion requirements (P = .009), and length of ICU stay (P = .04). No adverse events following UAE were noted. CONCLUSIONS: UAE following cesarean delivery but before hysterectomy in patients with placenta increta appears to be safe and effective in decreasing EBL, transfusion requirements, and length of ICU stay compared with C-hyst alone.

Percutaneous CT-guided vertebral bone biopsy in children.

BACKGROUND: Few published series are dedicated solely to CT-guided vertebral bone biopsy in children. OBJECTIVE: The objective of our study was to review the diagnostic yield of CT-guided vertebral bone biopsy in children. MATERIALS AND METHODS: A retrospective review of 26 consecutive CT-guided vertebral bone biopsies during a 7-year period in 24 children (16 girls and 8 boys), mean age 8.8 years (range 1-16 years) was performed at our institution. Procedures were reviewed for diagnostic accuracy, biopsy location, complications and final diagnosis. RESULTS: Twenty-five of 26 biopsies (96%) were technically successful. Twenty-one of 26 biopsies were diagnostic (81%); 2/26 (8%) were false-negative removing non-lesional tissue, 2/26 (8%) were nondiagnostic, and 1/26 (4%) was technically unsuccessful. The diagnoses were as follows: 12/26 biopsies (46%) were osteomyelitis, 3/26 (11%) biopsies were Langerhans cell histiocytosis, 3/26 biopsies (11%) were normal bone, 2/26 (8%) biopsies were malignant tumors, and 1/26 (4%) biopsies was osteoblastoma. There was one self-limited, procedure-related complication: a small right-sided pneumothorax occurred in the setting of attempting to create a protective extrapleural biopsy window. CONCLUSION: Percutaneous CT-guided vertebral bone biopsy can be performed safely in children with a high degree of diagnostic accuracy.

Percutaneous retrieval of intravascular venous foreign bodies in children.

BACKGROUND: The use of vascular lines both venous and arterial in children has significantly increased in the last decade with the potential risk that an intravascular device may become an intravascular foreign body. Percutaneous retrieval by interventional radiology has become an accepted method of foreign body removal. OBJECTIVE: The objective of this study is to describe a single center's experience of percutaneous intravascular foreign body removal in pediatric patients. MATERIALS AND METHODS: Between January 2000 and December 2008, 18 patients underwent percutaneous intravascular foreign body retrieval as a complication of venous access devices. The mean catheter days were 181.2 catheter days (1 to 1,146 days). A retrospective review was performed and demographic data and clinical information were recorded, including type, duration, location of access device, embolization location and retrieval technique. RESULTS: Eighteen of 19 (94.7%) retrievals were performed with single-loop snares and 1/19 (5.3%) was a triple-loop snare. Seventeen of 19 (89.5%) retrievals were successful. One unsuccessful retrieval was successfully removed by surgery, while the other was retained. CONCLUSION: Percutaneous intravascular foreign body retrieval by interventional radiologists is a safe and effective method of retrieving embolized fragments from venous access devices in pediatric patients.

Percutaneous sclerotherapy in neonatal and infant head and neck lymphatic malformations: a single center experience.

PURPOSE: To evaluate the clinical outcomes of percutaneous sclerotherapy for congenital head and neck lymphatic malformations in our institution. MATERIALS AND METHODS: Over a 7-year period, 17 children (10 M, 7 F) mean age 5.8 months (5 days to 13 months) underwent 49 sclerotherapy procedures for congenital head and neck malformations. The imaging and clinical records were reviewed for each patient. Ten of 17 had macrocystic disease; 7 of 17 had microcystic disease. Imaging response was categorized by volume reductions of 0% to 25%, 25% to 50%, 50% to 75%, or 75% to 100%. A concentration of 10 mg/mL doxycycline was used routinely via catheter in 3 instillations with a dose range of 50 to 500 mg per session as per our standard protocol in 17 of 17 patients. In more recent patients, systemic doxycycline levels were obtained after instillations. Additional treatments included direct injection doxycycline (10/17), instillation of absolute ethanol (7/17) or sodium tetradecyl sulfate (4/17), or a combination of these methods. RESULTS: Imaging improvement of ≥ 76% was noted in 11 of 17. Of these, 8 of 11 had macrocystic disease. Four of 17 had 51% to 75% resolution, of which 3/4 were mixed. Two of 17 children had 25% to 50% resolution with a mixed lesion. Seven of 49 peri-procedural complications: hemolytic anemia in 2 infants, hypoglycemic and metabolic acidosis in 3 neonates aged 7 to 10 days, transient hypotension during absolute alcohol instillation in 1 neonate, and self-limiting skin excoriation secondary to peri-catheter leakage of doxycycline in one neonate. Neonates prone to these systemic complications had doxycycline doses of greater than 250 mg and resulted in serum levels of >5 µg/mL but as high as 21 µg/mL. Delayed neural complications occurred in 7 of 49 procedures, Horner's syndromes in 4 of 49 procedures, transient left lip weakness in 1 of 49 procedures, right facial nerve palsy in 1 of 49 procedures, and transient left hemidiaphragm paralysis in 1/49 procedures. CONCLUSION: Our experience with catheter directed doxycycline sclerotherapy provides excellent results for large macrocystic head and neck lymphatic malformations. Microcystic and mixed lesions continue to provide a therapeutic challenge.

Vascular anomalies: what they are, how to diagnose them, and how to treat them.

Vascular anomalies are congenital lesions that most often first present in pediatric patients. Treatment of these lesions is a multidisciplinary team approach, involving several specialties, including diagnostic and interventional radiology, dermatology, general and plastic surgery, otolaryngology, and hematology. Knowing the characteristic findings of vascular anomalies on ultrasound, computed tomography, and magnetic resonance imaging leads to early, accurate diagnosis and therapeutic intervention of these lesions. This article discusses the gross and radiographic appearances and the latest treatment options for vascular anomalies.