Germany has a long history of insufficient iodine supply and thyroid nodules occur in over 30% of the adult population, the vast majority of which are benign. Non-invasive diagnostics remain challenging, and ultrasound-based risk stratification systems are essential for selecting lesions requiring further clarification. However, no recommendation can yet be made about which system performs the best for iodine deficiency areas. In a German multicenter approach, 1211 thyroid nodules from 849 consecutive patients with cytological or histopathological results were enrolled. Scintigraphically hyperfunctioning lesions were excluded. Ultrasound features were prospectively recorded, and the resulting classifications according to five risk stratification systems were retrospectively determined. Observations determined 1022 benign and 189 malignant lesions. The diagnostic accuracies were 0.79, 0.78, 0.70, 0.82, and 0.79 for Kwak Thyroid Imaging Reporting and Data System (Kwak-TIRADS), American College of Radiology (ACR) TI-RADS, European Thyroid Association (EU)-TIRADS, Korean-TIRADS, and American Thyroid Association (ATA) Guidelines, respectively. Receiver Operating Curves revealed Areas under the Curve of 0.803, 0.795, 0.800, 0.805, and 0.801, respectively. According to the ATA Guidelines, 135 thyroid nodules (11.1%) could not be classified. Kwak-TIRADS, ACR TI-RADS, and Korean-TIRADS outperformed EU-TIRADS and ATA Guidelines and therefore can be primarily recommended for non-autonomously functioning lesions in areas with a history of iodine deficiency.

The classification of thyroid nodules using ultrasound (US) imaging is done using the Thyroid Imaging Reporting and Data System (TIRADS) guidelines that classify nodules based on visual and textural characteristics. These are composition, shape, size, echogenicity, calcifications, margins, and vascularity. This work aims to reduce subjectivity in the current diagnostic process by using geometric and morphological (G-M) features that represent the visual characteristics of thyroid nodules to provide physicians with decision support. A total of 27 G-M features were extracted from images obtained from an open-access US thyroid nodule image database. 11 significant features in accordance with TIRADS were selected from this global feature set. Each feature was labeled (0 = benign and 1 = malignant) and the performance of the selected features was evaluated using machine learning (ML). G-M features together with ML resulted in the classification of thyroid nodules with a high accuracy, sensitivity and specificity. The results obtained here were compared against state-of the-art methods and perform significantly well in comparison. Furthermore, this method can act as a computer aided diagnostic (CAD) system for physicians by providing them with a validation of the TIRADS visual characteristics used for the classification of thyroid nodules in US images.

Due to the widespread use of ultrasound, small thyroid nodules (TNs) ≤ 10 mm are common findings. Standardized approaches for the risk stratification of TNs with Thyroid Imaging Reporting and Data Systems (TIRADS) were evaluated for the clinical routine. With TIRADS, the risk of malignancy in TNs is calculated by scoring the number or combination of suspicious ultrasound features, leading to recommendations for further diagnostic steps. However, there are only scarce data on the performance of TIRADS for small TNs. The aim was to compare three different TIRADS for risk stratification of small TNs in routine clinical practice. We conducted a retrospective cohort analysis of TNs ≤ 10 mm and their available histology. Nodules were classified according to three different TIRADS. In the study, 140 patients (n = 113 female) with 145 thyroid nodules (n = 76 malignant) were included. Most of the malignant nodules were papillary carcinoma (97%), and the remaining 3% were medullary carcinoma. For all tested TIRADS, the prevalence of malignancy rose with increasing category levels. The highest negative predictive value was found for ACR TI-RADS and the highest positive predictive value for Kwak-TIRADS. All tested variants of TIRADS showed comparable diagnostic performance for the risk stratification of small TNs. TIRADS seems to be a promising tool to reliably assess the risk of malignancy of small TNs.

The bone scan index (BSI), initially introduced for metastatic prostate cancer, quantifies the osseous tumor load from planar bone scans. Following the basic idea of radiomics, this method incorporates specific deep-learning techniques (artificial neural network) in its development to provide automatic calculation, feature extraction, and diagnostic support. As its performance in tumor entities, not including prostate cancer, remains unclear, our aim was to obtain more data about this aspect. The results of BSI evaluation of bone scans from 951 consecutive patients with different tumors were retrospectively compared to clinical reports (bone metastases, yes/no). Statistical analysis included entity-specific receiver operating characteristics to determine optimized BSI cut-off values. In addition to prostate cancer (cut-off = 0.27%, sensitivity (SN) = 87%, specificity (SP) = 99%), the algorithm used provided comparable results for breast cancer (cut-off 0.18%, SN = 83%, SP = 87%) and colorectal cancer (cut-off = 0.10%, SN = 100%, SP = 90%). Worse performance was observed for lung cancer (cut-off = 0.06%, SN = 63%, SP = 70%) and renal cell carcinoma (cut-off = 0.30%, SN = 75%, SP = 84%). The algorithm did not perform satisfactorily in melanoma (SN = 60%). For most entities, a high negative predictive value (NPV ≥ 87.5%, melanoma 80%) was determined, whereas positive predictive value (PPV) was clinically not applicable. Automatically determined BSI showed good sensitivity and specificity in prostate cancer and various other entities. Particularly, the high NPV encourages applying BSI as a tool for computer-aided diagnostic in various tumor entities.

Article: Update on diagnosis and treatment of hyperthyroidism: ultrasonography and functional imaging - The Quarterly Journal of Nuclear Medicine and Molecular Imaging 2021 June;65(2):102-12 - Minerva Medica - Journals

In conventional thyroid diagnostics, the topographical correlation between thyroid nodules (TN) depicted on ultrasound (US) in axial or sagittal orientation and coronally displayed scintigraphy images can be challenging. Sensor-navigated I-124-PET/US fusion imaging has been introduced as a problem-solving tool for ambiguous cases. The purpose of this study was to investigate the results of multiple unexperienced medical students (MS) versus multiple nuclear medicine physicians (MD) regarding the overvalue of I-124-PET/US in comparison to conventional diagnostics (CD) for the functional assessment of TN. Methods: Out of clinical routine, cases with ambiguous findings on CD were selected for I-124-PET/US fusion imaging. Sixty-eight digital patient case files (PCF) of 34 patients (CDonly and CD+PET/US PCF) comprising 66 TN were provided to be retrospectively evaluated by 70 MD and 70 MS, respectively. A total of 2174 ratings (32.9 per TN) were carried out: 555 ratings (8.4 per TN) for CDonly and 532 ratings (8.1 per TN) for CD+PET/US by each MD and MS. Results: Functional assessment revealed 8.5%/11.7% (n.s.) (16.4%/25.8% (p = 0.0002)), 41.8%/28.5% (p < 0.0001) (23.9%/17.9% (p = 0.0193)), 36.0%/30.5% (n.s.) (57.3%/53.9% (n.s.)), and 13.7%/29.4% (p < 0.0001) (2.4%/2.4% (n.s.)) hyperfunctioning, indifferent, hypofunctioning, and not rateable TNs for CDonly (CD+PET/US) and MD/MS, respectively. The respective rating confidence was indicated as absolute certain, quite certain, equivocal, uncertain, and not rateable in 11.7/3.4% (p < 0.0001) (44.9%/38.9% (p = 0.0541), 51.9%/26.7% (p < 0.0001) (46.2%/41.5% (n.s.)), 21.6%/29.0% (p = 0.0051) (6.2%/14.8% (p < 0.0001)), 1.1%/11.5% (p < 0.0001) (0.2%/2.3% (p = 0.0032)), and 13.7%/29.4% (p < 0.0001) (2.4%/2.4% (n.s.)) by MD/MS, respectively. There was a significant difference in the diversity of the observers’ functional assessment of TN (MD 0.84 vs. MS 1.02, p = 0.0006) and the respective confidence in functional assessment (MD 0.93 vs. MS 1.16, p < 0.0001) between MD and MS on CDonly, whereas CD+PET/US revealed weaker differences for both groups (MD 0.48 vs. MS 0.47, p = 0.57; and MD 0.66 vs. MS 0.83, p = 0.0437). With the additional application of I-124-PET/US, the rating diversity of both MD and MS markedly tends towards more consistency (p < 0.0001 in each case). Conclusion: The additional application of sensor-navigated I-124-PET/US fusion imaging significantly influenced the functional assessment of TN positively, especially for unexperienced observers.