Search

Background: Hepatocellular carcinoma (HCC) is a prevalent tumor with high mortality rates. Computed tomography (CT) is crucial in the non-invasive diagnosis of HCC. Recent advancements in artificial intelligence (AI) have shown significant potential in medical imaging analysis. However, developing these AI algorithms is hindered by the scarcity of comprehensive, publicly available liver imaging datasets., Objectives: This study aims to detail the tools, data organization, and database structuring used in creating HepatIA, a medical imaging annotation platform and database at a Brazilian tertiary teaching hospital. HepatIA supports liver disease AI research at the institution., Material and Methods: The authors collected baseline characteristics and CT scans of 656 patients from 2008 to 2021. The database, designed using PostgreSQL and implemented with Django and Vue.js, includes 692 CT volumes from a four-phase abdominal CT protocol. Radiologists made segmentation annotations using the OHIF medical image viewer, incorporating MONAI Label for pre-annotation segmentation models. The annotation process included detailed descriptions of liver morphology and nodule characteristics., Results: The HepatIA database currently includes healthy individuals and those with liver diseases such as HCC and cirrhosis. The database dashboard facilitates user interaction with intuitive plots and histograms. Key patient demographics include 64% males and an average age of 56.89 years. The database supports various filters for detailed searches, enhancing research capabilities., Conclusion: A comprehensive data structure was successfully created and integrated with the IT systems of a teaching hospital, enabling research on deep learning algorithms applied to abdominal CT scans for investigating hepatic lesions such as HCC., Competing Interests: Declaration of competing interest The authors B.A.R., L.G.R.V., and A.C.M.C. are co-founders of Machiron SA. FMUSP, HCFMUSP, and Machiron SA. have established a collaborative partnership, with the terms of this arrangement having been reviewed and approved by the University of São Paulo in accordance with its conflict-of-interest policies. Meanwhile, L.C.F., J.M.C.F., L.S.L.N., M.R.M.S.F., C.C.L., C.H.N., G.G.C., F.J.C., and S.K.O. have declared no competing interests., (Copyright © 2024 HCFMUSP. Published by Elsevier España, S.L.U. All rights reserved.)

Hepatocellular carcinoma (HCC) has become the 4th leading cause of cancer-related deaths, with high social, economical and health implications. Imaging techniques such as multiphase computed tomography (CT) have been successfully used for diagnosis of liver tumors such as HCC in a feasible and accurate way and its interpretation relies mainly on comparing the appearance of the lesions in the different contrast phases of the exam. Recently, some researchers have been dedicated to the development of tools based on machine learning (ML) algorithms, especially by deep learning techniques, to improve the diagnosis of liver lesions in imaging exams. However, the lack of standardization in the naming of the CT contrast phases in the DICOM metadata is a problem for real-life deployment of machine learning tools. Therefore, it is important to correctly identify the exam phase based only on the image and not on the exam metadata, which is unreliable. Motivated by this problem, we successfully created an annotation platform and implemented a convolutional neural network (CNN) to automatically identify the CT scan phases in the HCFMUSP database in the city of São Paulo, Brazil. We improved this algorithm with hyperparameter tuning and evaluated it with cross validation methods. Comparing its predictions with the radiologists annotation, it achieved an accuracy of 94.6%, 98% and 100% in the testing dataset for the slice, volume and exam evaluation, respectively., (© 2022. The Author(s).)

Purpose: To evaluate an MRI-based radiomic texture classifier alone and combined with radiologist qualitative assessment in predicting pathological complete response (pCR) using restaging MRI with internal training and external validation., Methods: Consecutive patients with locally advanced rectal cancer (LARC) who underwent neoadjuvant therapy followed by total mesorectal excision from March 2012 to February 2016 (Memorial Sloan Kettering Cancer Center/internal dataset, n = 114, 41% female, median age = 55) and July 2014 to October 2015 (Instituto do Câncer do Estado de São Paulo/external dataset, n = 50, 52% female, median age = 64.5) were retrospectively included. Two radiologists (R1, senior; R2, junior) independently evaluated restaging MRI, classifying patients (radiological complete response vs radiological partial response). Model A (n = 33 texture features), model B (n = 91 features including texture, shape, and edge features), and two combination models (model A + B + R1, model A + B + R2) were constructed. Pathology served as the reference standard for neoadjuvant treatment response. Comparison of the classifiers' AUCs on the external set was done using DeLong's test., Results: Models A and B had similar discriminative ability (P = 0.3; Model B AUC = 83%, 95% CI 70%-97%). Combined models increased inter-reader agreement compared with radiologist-only interpretation (κ = 0.82, 95% CI 0.70-0.89 vs k = 0.25, 95% CI 0.11-0.61). The combined model slightly increased junior radiologist specificity, positive predictive value, and negative predictive values (93% vs 90%, 57% vs 50%, and 91% vs 90%, respectively)., Conclusion: We developed and externally validated a combined model using radiomics and radiologist qualitative assessment, which improved inter-reader agreement and slightly increased the diagnostic performance of the junior radiologist in predicting pCR after neoadjuvant treatment in patients with LARC., (© 2022. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)

Objectives: To evaluate the diagnostic performance and interobserver agreement of PI-RADS v2., Materials and Methods: In this Institutional Review Board approved single-center retrospective study, 98 patients with clinically suspected PCa who underwent 3-T multiparametric MRI followed by MRI/TRUS fusion-guided prostate biopsy were included from June 2013 to February 2015. Two radiologists (R1 and R2) with 8 and 1 years of experience in abdominal radiology reviewed the MRI scans and assigned PI-RADS v2 scores in all prostate zones. PI-RADS v2 were compared to MRI/TRUS fusion-guided biopsy results, which were classified as negative, PCa, and significant PCa (sPCa)., Results: Sensitivity, specificity, NPV, PPV and accuracy for PCa was 85.7% (same for all metrics) for R1 and 81.6%, 79.6%, 81.2%, 80.0% and 80.6% for R2. For detecting sPCa, the corresponding values were 95.3%, 85.4%, 95.9%, 83.7% and 89.8% for R1 and 93.0%, 81.8%, 93.7%, 86.7% and 86.7% for R2. There was substantial interobserver agreement in assigning PI-RADS v2 score as negative (1, 2, 3) or positive (4, 5) (Kappa=0.78). On multivariate analysis, PI-RADS v2 (p <0.001) was the only independent predictor of sPCa compared with age, abnormal DRE, prostate volume, PSA and PSA density., Conclusions: Our study population demonstrated that PI-RADS v2 had high diagnostic accuracy, substantial interobserver agreement, and it was the only independent predictor of sPCa., Competing Interests: None declared., (Copyright® by the International Brazilian Journal of Urology.)

In the current context of epidemiological transition, demographic changes, changes in consumption and lifestyle habits, and pressure on care costs and organized health systems for acute conditions, the Integrated Care Model by Shortell has become a conceptual reference in the search for new methods to manage chronic conditions by focusing on the health conditions of a given population that must be addressed by a set of institutions organized into networks. Within the last 15 years, cancer has gone from the third- to the second-leading cause of death in the State of São Paulo and has shown a gradual increase in the number of new cases; it has thus become a relevant issue for public health and health management. The model adopted by the State for the organization of the cancer care network was the motivation for this study, which aimed to evaluate the evolution of the model of care for cancer patients within the Unified Health System (Sistema Único de Saúde) based on the integrated care model. Since 1993, the year that cancer was first considered highly complex in the Sistema Único de Saúde by the Ministry of Health, it has been possible to observe a progressive orientation towards the integral and integrated care of patients with cancer. In the State of São Paulo, the active participation of qualified service providers through a Technical Reference Committee showed that experts could contribute to the definition of public policies, thereby providing a technical base for decision making and contributing to the development of clinical management.

Purpose: To show that prostatic artery embolization (PAE) improves quality of life (QoL) and lower urinary tract symptoms in patients with acute urinary retention caused by benign prostatic hyperplasia (BPH)., Materials and Methods: This was a single-center prospective study of PAE in 11 patients with BPH managed with indwelling urinary catheters. International Prostate Symptom Score (IPSS), ultrasound, magnetic resonance (MR) imaging, QoL, and urodynamic tests were used to assess outcomes. Prostate size ranged from 30 to 90 g, and embolizations were performed with 300-500-μm Embosphere microspheres., Results: The rate of technical success (ie, bilateral PAE) was 75%, and the rate of clinical success (ie, catheter removal and symptom improvement) was 91% (10 of 11 patients). Postembolization syndrome manifested as mild pain in the perineum, retropubic area, and/or urethra. Ten of 11 patients urinated spontaneously after Foley catheter removal 4-25 days after PAE (mean, 12.1 d). No major complications were observed. Follow-up ranged from 19 to 48 months. In an asymptomatic patient, a discrete area of hypoperfusion suggesting small ischemia of the bladder was observed on 30-day MR imaging follow-up, but the bladder was normal on 90-day MR imaging. After 1 year, mean prostate volume reduction was greater than 30%, symptoms were mild (mean IPSS, 2.8 ± 2.1; P = .04), no erectile dysfunction was observed, and QoL improved significantly (mean, 0.4 ± 0.5; P = .001) using the paired t test., Conclusions: Patients with severe symptoms and acute urinary retention caused by BPH can be treated safely by PAE, which improves clinical symptoms and QoL., (Copyright © 2013 SIR. Published by Elsevier Inc. All rights reserved.)

Objective: The purpose of this study was to assess the agreement between 3-dimensional ultrasonography (3DUS) and magnetic resonance imaging (MRI) for lung volumetry in fetuses with and without abnormalities associated with lung hypoplasia., Methods: Fifty-nine singleton pregnancies were evaluated. Cases were separated into groups 1 and 2, according to the presence or absence of malformations associated with lung hypoplasia, respectively. Fetal lung volume was calculated by the Virtual Organ Computer-Aided Analysis (VOCAL) program of the 3DUS and the MRI. In both groups, measurements performed with all VOCAL angles were compared among themselves and with those obtained by MRI. Bland-Altman tests and analysis of variance were used for this purpose., Results: In groups 1 and 2, the mean lung volume obtained with each rotation angle of the VOCAL technique was significantly smaller than the mean volume calculated by MRI (P < .001), and the mean volume obtained with the 30 degrees rotation step was significantly smaller than those obtained with the other rotation steps of the VOCAL technique. Bland-Altman tests confirmed this underestimation and showed a broad 95% confidence interval when the VOCAL angles were compared with those of MRI and when the 30 degrees rotation step was compared with the other VOCAL steps., Conclusions: There was a substantial discrepancy between 3DUS and MRI and between the 30 degrees rotation step of the VOCAL technique and the other rotation angles, for lung volume measurement in fetuses with and without abnormalities associated with lung hypoplasia.