Artificial intelligence-based analysis of whole-body bone scintigraphy: The quest for the optimal deep learning algorithm and comparison with human observer performance.

PURPOSE: Whole-body bone scintigraphy (WBS) is one of the most widely used modalities in diagnosing malignant bone diseases during the early stages. However, the procedure is time-consuming and requires vigour and experience. Moreover, interpretation of WBS scans in the early stages of the disorders might be challenging because the patterns often reflect normal appearance that is prone to subjective interpretation. To simplify the gruelling, subjective, and prone-to-error task of interpreting WBS scans, we developed deep learning (DL) models to automate two major analyses, namely (i) classification of scans into normal and abnormal and (ii) discrimination between malignant and non-neoplastic bone diseases, and compared their performance with human observers. MATERIALS AND METHODS: After applying our exclusion criteria on 7188 patients from three different centers, 3772 and 2248 patients were enrolled for the first and second analyses, respectively. Data were split into two parts, including training and testing, while a fraction of training data were considered for validation. Ten different CNN models were applied to single- and dual-view input (posterior and anterior views) modes to find the optimal model for each analysis. In addition, three different methods, including squeeze-and-excitation (SE), spatial pyramid pooling (SPP), and attention-augmented (AA), were used to aggregate the features for dual-view input models. Model performance was reported through area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and specificity and was compared with the DeLong test applied to ROC curves. The test dataset was evaluated by three nuclear medicine physicians (NMPs) with different levels of experience to compare the performance of AI and human observers. RESULTS: DenseNet121_AA (DensNet121, with dual-view input aggregated by AA) and InceptionResNetV2_SPP achieved the highest performance (AUC = 0.72) for the first and second analyses, respectively. Moreover, on average, in the first analysis, Inception V3 and InceptionResNetV2 CNN models and dual-view input with AA aggregating method had superior performance. In addition, in the second analysis, DenseNet121 and InceptionResNetV2 as CNN methods and dual-view input with AA aggregating method achieved the best results. Conversely, the performance of AI models was significantly higher than human observers for the first analysis, whereas their performance was comparable in the second analysis, although the AI model assessed the scans in a drastically lower time. CONCLUSION: Using the models designed in this study, a positive step can be taken toward improving and optimizing WBS interpretation. By training DL models with larger and more diverse cohorts, AI could potentially be used to assist physicians in the assessment of WBS images.

CAD system based on B-mode and color Doppler sonographic features may predict if a thyroid nodule is hot or cold.

OBJECTIVES: The aim of this study was to evaluate if the analysis of sonographic parameters could predict if a thyroid nodule was hot or cold. METHODS: Overall, 102 thyroid nodules, including 51 hyperfunctioning (hot) and 51 hypofunctioning (cold) nodules, were evaluated in this study. Twelve sonographic features (i.e., seven B-mode and five Doppler features) were extracted for each nodule type. The isthmus thickness, nodule volume, echogenicity, margin, internal component, microcalcification, and halo sign features were obtained in the B-mode, while the vascularity pattern, resistive index (RI), peak systolic velocity, end diastolic velocity, and peak systolic/end diastolic velocity ratio (SDR) were determined, based on Doppler ultrasounds. All significant features were incorporated in the computer-aided diagnosis (CAD) system to classify hot and cold nodules. RESULTS: Among all sonographic features, only isthmus thickness, nodule volume, echogenicity, RI, and SDR were significantly different between hot and cold nodules. Based on these features in the training dataset, the CAD system could classify hot and cold nodules with an area under the curve (AUC) of 0.898. Also, in the test dataset, hot and cold nodules were classified with an AUC of 0.833. CONCLUSIONS: 2D sonographic features could differentiate hot and cold thyroid nodules. The CAD system showed a great potential to achieve it automatically. KEY POINTS: • Cold nodules represent higher volume (p = 0.005), isthmus thickness (p = 0.035), RI (p = 0.020), and SDR (p = 0.044) and appear hypoechogenic (p = 0.010) in US. • Nodule volume with an AUC of 0.685 and resistive index with an AUC of 0.628 showed the highest classification potential among all B-mode and Doppler features respectively. • The proposed CAD system could distinguish hot nodules from cold ones with an AUC of 0.833 (sensitivity 90.00%, specificity 70.00%, accuracy 80.00%, PPV 87.50%, and NPV 75.00%).

COMPARE CPM-RMI Trial: Intramyocardial Transplantation of Autologous Bone Marrow-Derived CD133+ Cells and MNCs during CABG in Patients with Recent MI: A Phase II/III, Multicenter, Placebo-Controlled, Randomized, Double-Blind Clinical Trial.

This article published in Cell J (Yakhteh), Vol 20, No 2, Jul-Sep 2018, on pages 267-277, four affiliations (1, 4, 5, and 10) were changed based on authors request.

COMPARE CPM-RMI Trial: Intramyocardial Transplantation of Autologous Bone Marrow-Derived CD133+ Cells and MNCs during CABG in Patients with Recent MI: A Phase II/III, Multicenter, Placebo-Controlled, Randomized, Double-Blind Clinical Trial.

OBJECTIVES: The regenerative potential of bone marrow-derived mononuclear cells (MNCs) and CD133+ stem cells in the heart varies in terms of their pro-angiogenic effects. This phase II/III, multicenter and double-blind trial is designed to compare the functional effects of intramyocardial autologous transplantation of both cell types and placebo in patients with recent myocardial infarction (RMI) post-coronary artery bypass graft. MATERIALS AND METHODS: This was a phase II/III, randomized, double-blind, placebo-controlled trial COMPARE CPM-RMI (CD133, Placebo, MNCs - recent myocardial infarction) conducted in accordance with the Declaration of Helsinki that assessed the safety and efficacy of CD133 and MNCs compared to placebo in patients with RMI. We randomly assigned 77 eligible RMI patients selected from 5 hospitals to receive CD133+ cells, MNC, or a placebo. Patients underwent gated single photon emission computed tomography assessments at 6 and 18 months post-intramyocardial transplantation. We tested the normally distributed efficacy outcomes with a mixed analysis of variance model that used the entire data set of baseline and between-group comparisons as well as within subject (time) and group×time interaction terms. RESULTS: There were no related serious adverse events reported. The intramyocardial transplantation of both cell types increased left ventricular ejection fraction by 9% [95% confidence intervals (CI): 2.14% to 15.78%, P=0.01] and improved decreased systolic wall thickening by -3.7 (95% CI: -7.07 to -0.42, P=0.03). The CD133 group showed significantly decreased non-viable segments by 75% (P=0.001) compared to the placebo and 60% (P=0.01) compared to the MNC group. We observed this improvement at both the 6- and 18-month time points. CONCLUSIONS: Intramyocardial injections of CD133+ cells or MNCs appeared to be safe and efficient with superiority of CD133+ cells for patients with RMI. Although the sample size precluded a definitive statement about clinical outcomes, these results have provided the basis for larger studies to confirm definitive evidence about the efficacy of these cell types (Registration Number: NCT01167751).

Predictive quantitative sonographic features on classification of hot and cold thyroid nodules.

PURPOSE: This study investigated the potentiality of ultrasound imaging to classify hot and cold thyroid nodules on the basis of textural and morphological analysis. METHODS: In this research, 42 hypo (hot) and 42 hyper-function (cold) thyroid nodules were evaluated through the proposed method of computer aided diagnosis (CAD) system. To discover the difference between hot and cold nodules, 49 sonographic features (9 morphological, 40 textural) were extracted. A support vector machine classifier was utilized for the classification of LNs based on their extracted features. RESULTS: In the training set data, a combination of morphological and textural features represented the best performance with area under the receiver operating characteristic curve (AUC) of 0.992. Upon testing the data set, the proposed model could classify the hot and cold thyroid nodules with an AUC of 0.948. CONCLUSIONS: CAD method based on textural and morphological features is capable of distinguishing between hot from cold nodules via 2-Dimensional sonography. Therefore, it can be used as a supplementary technique in daily clinical practices to improve the radiologists' understanding of conventional ultrasound imaging for nodules characterization.

Solitary metastasis of gastric cancer to fibula: a case report.

Gastric cancer is one of the most common and most fatal neoplasms in human. Its skeletal metastasis is less frequent, particularly when solitary. The objective of this article is to represent a case of solitary fibular metastasis from this cancer not reported before based on Medline search.

Urine macrophage migration inhibitory factor (MIF) in children with urinary tract infection: a possible predictor of acute pyelonephritis.

Macrophage migration inhibitory factor (MIF) is an important pro-inflammatory cytokine expressed at sites of inflammation. We have assessed this factor (MIF) in urinary tract infections with the aim of determining a non-invasive and sensitive method to differentiate upper and lower renal involvement. Thirty-three pediatric patients with urinary track infection (25 with acute pyelonephritis, eight with acute cystitis) and 40 healthy subjects were recruited for this prospective case-control study. Pyelonephritis was differentiated from cystitis by dimercaptosuccinic acid (DMSA) scan. Urinary MIF concentration was determined using an enzyme-linked immunosorbent assay method. The urine MIF/creatinine (Cr) ratio was significantly higher in pyelonephritis patients than in those with acute cystitis and the control group (P < 0.001). The optimal cut-point of 4.90 pg/micromol Cr for the urine MIF/Cr ratio has the potential to be a biomarker for distinguishing patients with acute pyelonephritis from those with acute cystitis. Determination of the urinary MIF was also useful in selecting the patients at risk of permanent renal damage. Of those patients with pyelonephritis, based on the DMSA scan at the time of infection, scarring on follow-up DMSA scan 9-12 months later occurred in patients with the highest urinary MIF/Cr ratios. We conclude that the urine MIF/Cr ratio is a sensitive test for differentiating acute pyelonephritis from acute cystitis and also for detecting children with acute pyelonephritis who are at a higher risk for permanent renal scars in the future.