Which needle in the treatment of thyroid nodules?

Texture and shape analysis of diffusion-weighted imaging for thyroid nodules classification using machine learning

PURPOSE

To assess whether the integration between (a) functional imaging features that will be extracted from diffusion-weighted imaging (DWI); and (b) shape and texture imaging features as well as volumetric features that will be extracted from T2-weighted magnetic resonance imaging (MRI) can noninvasively improve the diagnostic accuracy of thyroid nodules classification.

PATIENTS AND METHODS

In a retrospective study of 55 patients with pathologically proven thyroid nodules, T2-weighted and diffusion-weighted MRI scans of the thyroid gland were acquired. Spatial maps of the apparent diffusion coefficient (ADC) were reconstructed in all cases. To quantify the nodules' morphology, we used spherical harmonics as a new parametric shape descriptor to describe the complexity of the thyroid nodules in addition to traditional volumetric descriptors (e.g., tumor volume and cuboidal volume). To capture the inhomogeneity of the texture of the thyroid nodules, we used the histogram-based statistics (e.g., kurtosis, entropy, skewness, etc.) of the T2-weighted signal. To achieve the main goal of this paper, a fusion system using an artificial neural network (NN) is proposed to integrate both the functional imaging features (ADC) with the structural morphology and texture features. This framework has been tested on 55 patients (20 patients with malignant nodules and 35 patients with benign nodules), using leave-one-subject-out (LOSO) for training/testing validation tests.

RESULTS

The functionality, morphology, and texture imaging features were estimated for 55 patients. The accuracy of the computer-aided diagnosis (CAD) system steadily improved as we integrate the proposed imaging features. The fusion system combining all biomarkers achieved a sensitivity, specificity, positive predictive value, negative predictive value, F1-score, and accuracy of 92.9 % (confidence interval [CI]: 78.9 % -- 99.5 % ), 95.8 % (CI: 87.4 % -- 99.7 % ), 93 % (CI: 80.7 % -- 99.5 % ), 96 % (CI: 88.8 % -- 99.7 % ), 92.8 % (CI: 83.5 % -- 98.5 % ), and 95.5 % (CI: 88.8 % -- 99.2 % ), respectively, using the LOSO cross-validation approach.

CONCLUSION

The results demonstrated in this paper show the promise that integrating the functional features with morphology as well as texture features by using the current state-of-the-art machine learning approaches will be extremely useful for identifying thyroid nodules as well as diagnosing their malignancy.

Novel MRI-Based CAD System for Early Detection of Thyroid Cancer Using Multi-Input CNN

Early detection of thyroid nodules can greatly contribute to the prediction of cancer burdening and the steering of personalized management. We propose a novel multimodal MRI-based computer-aided diagnosis (CAD) system that differentiates malignant from benign thyroid nodules. The proposed CAD is based on a novel convolutional neural network (CNN)-based texture learning architecture. The main contribution of our system is three-fold. Firstly, our system is the first of its kind to combine T2-weighted MRI and apparent diffusion coefficient (ADC) maps using a CNN to model thyroid cancer. Secondly, it learns independent texture features for each input, giving it more advanced capabilities to simultaneously extract complex texture patterns from both modalities. Finally, the proposed system uses multiple channels for each input to combine multiple scans collected into the deep learning process using different values of the configurable diffusion gradient coefficient. Accordingly, the proposed system would enable the learning of more advanced radiomics with an additional advantage of visualizing the texture patterns after learning. We evaluated the proposed system using data collected from a cohort of 49 patients with pathologically proven thyroid nodules. The accuracy of the proposed system has also been compared against recent CNN models as well as multiple machine learning (ML) frameworks that use hand-crafted features. Our system achieved the highest performance among all compared methods with a diagnostic accuracy of 0.87, specificity of 0.97, and sensitivity of 0.69. The results suggest that texture features extracted using deep learning can contribute to the protocols of cancer diagnosis and treatment and can lead to the advancement of precision medicine.

Comparative efficacy of different ultrasound-guided ablation for the treatment of benign thyroid nodules: Systematic review and network meta-analysis of randomized controlled trials

BACKGROUND

Percutaneous ablation is currently deemed an additionally treatment option for benign thyroid nodules in the world, but possibly different effect among the ablation modalities is not clear. So we aim to evaluate the efficacy and complications of thermal/chemical ablation by network meta-analysis.

MATERIALS AND METHODS

In the network meta-analysis, PubMed, EMBASE and the Cochrane Library databases were searched from 1980 to 2020. Studies of adults with thyroid benign nodules under percutaneous ablation therapy were included. Percentage mean volume change, symptom score change, cosmetic score change and complications were evaluated by network meta-analysis.

RESULTS

In the network meta-analysis, Radiofrequency Ablation(RFA) with 2 treatment sessions group was associated with the highest reduction for the mean volume change during 6-month follow-up (MD = 79.09 and 95% CrI:48.23-89.94). There is no significant difference in the incidence of complications. Subgroup analysis showed that 2 sessions of Radiofrequency Ablation (RFA) ranks the highest probability (surface under the cumulative ranking curve (SUCRA) values 77.9) of being the most efficacious treatment for solid or predominantly solid benign nodules. Ethanol ablation (EA) ranked first (SUCRA value 81.1) in the treatment for cyst or predominantly cyst benign nodules.

CONCLUSION

RFA appears to be superior to other US-guided percutaneous ablation in reducing benign thyroid nodule volume during short- and long-term follow-up. In the subgroup analysis, RFA with 2 treatment sessions showed the most significant effectiveness for solid benign thyroid nodules and EA showed more effectiveness to decrease the volume of cyst benign thyroid nodules.

Laser and radiofrequency ablations for benign and malignant thyroid tumors

A growing body of evidence is being published regarding the safety and efficacy of minimally invasive image-guided ablation techniques. While clinical applications of these techniques are increasing, international societies have started to publish treatment guidelines and to make efforts to standardize both terminology and reporting criteria for image-guided thyroid ablations. Laser ablation and radiofrequency ablation (RFA) are among the most common ablation techniques either for benign and malignant thyroid nodules. Unlike laser ablation and RFA in the treatment of benign thyroid nodules, where safety and efficacy have been widely demonstrated, evidence regarding local tumor control of thyroid malignancies is still limited. However, preliminary results are encouraging and image-guided thermal ablation techniques can be considered a valid alternative to surgery for the treatment of benign thyroid nodules and recurrent thyroid cancers. This review evaluates the basic concept of RFA and laser ablations, their techniques, clinical outcomes, and complications based on the suggestions of several society guidelines. Multidisciplinary collaboration remains critical to identify patients which may benefit from minimally invasive image-guided thermal ablations, especially if surgery or radioiodine therapy are not feasible options.

Image-Guided Thermal Ablation as an Alternative to Surgery for Papillary Thyroid Microcarcinoma: Preliminary Results of an Italian Experience

PURPOSE

To report the results of our preliminary experience in treating patients with papillary thyroid microcarcinoma (PTMC) with image-guided thermal ablation, in particular estimating the feasibility, safety and short-term efficacy.

MATERIALS AND METHODS

From 2018 patients with cytologically proven PTMC < 10 mm were discussed in a multidisciplinary team and evaluated for feasibility of image-guided thermal ablation. In case of technical feasibility, the three possible alternatives (i.e., image-guided thermal ablation, surgery, and active surveillance) were discussed with patients. Patients who agreed to be treated with image guided thermal ablation underwent radiofrequency (RFA) or laser ablation under local anesthesia and conscious sedation. Treatment feasibility, technical success, technique efficacy, change in thyroid function tests, side effects, minor and major complications, patients satisfaction and pain/discomfort perception during and after treatment, and disease recurrence during follow-up were recorded.

RESULTS

A total of 13 patients were evaluated, and 11/13 (84.6%) patients (9 female, 2 male, mean age 49.3 ± 8.7 years) resulted suitable for image-guided thermal ablation. All 11 patients agreed to be treated with image-guided thermal ablation. In addition, 3/11 (27.3%) were treated with laser ablation and 8/11 (72.7%) with RFA. All procedures were completed as preoperatively planned (technical success 100%). Technique efficacy was achieved in all 11/11 (100%) cases. Ablated volume significantly reduced from 0.87 ± 0.67 ml at first follow-up to 0.17 ± 0.36 at last follow-up (p = 0.003). No change in thyroid function tests occurred. No minor or major complications occurred. All patients graded 10 the satisfaction for the treatment, and mean pain after the procedure was reported as 1.4 ± 1.7, and mean pain after the procedure as 1.2 ± 1.1 At a median follow-up of 10.2 months (range 1.5-12 months), no local recurrence or distant metastases were found.

CONCLUSIONS

Image guided thermal ablations appear to be feasible and safe in the treatment of PTMC. These techniques hold the potential to offer patients a minimally invasive curative alternative to surgical resection or active surveillance. These techniques appear to be largely preferred by patients.

Clinical practice guidelines on ultrasound-guided fine needle aspiration biopsy of thyroid nodules: a critical appraisal using AGREE II

PURPOSE

To appraise the quality of current guidelines on fine needle aspiration biopsy (FNAB) of thyroid nodules for adults using the AGREE II quality assessment tool.

METHODS

We conducted an online search for guidelines on FNAB of thyroid nodules published between 2013 and October 2018. They were evaluated by four independent reviewers previously trained to apply the AGREE II instrument, which is organized into items and domains. A fifth independent reviewer calculated scores for each domain and guideline as well as inter-appraiser agreement.

RESULTS

Six sets of guidelines were included, respectively, provided by the American Thyroid Association (ATA), the American Association of Clinical Endocrinologists/American College of Endocrinology/Associazione Medici Endocrinologi (AACE/ACE/AME), the Korean Society of Thyroid Radiology (KSThR), the European Thyroid Association (ETA), the American College of Radiology (ACR) and the Korean Society of Radiology and National Evidence-Based Healthcare Collaborating Agency (KSR/NECA). Five out of the six guidelines (ATA, AACE/ACE/AME, ETA, ACR and KSR/NECA) reached a high level of overall quality, having at least five domain scores >60%. An average level of overall quality was achieved in one case (KSThR recommendations). Inter-appraiser agreement ranged from moderate to excellent.

CONCLUSIONS

Overall, the quality of guidelines on FNAB of thyroid nodules is satisfactory when evaluated using the AGREE II instrument.

Endoscopic radiofrequency biliary ablation treatment: A comprehensive review

Radiofrequency ablation (RFA) functions by delivering thermal energy within tissue, the result of a high-frequency alternating current released from an active electrode, leading to coagulative necrosis and cellular death. Recently, a biliary catheter working on a guidewire has been developed and a number of studies have so far been carried out. The present article provides a comprehensive review of the literature on the results of the use of RFA for the clinical management of patients with unresectable malignant biliary strictures, benign biliary strictures, and residual adenomatous tissue in the bile duct after endoscopic papillectomy. Available data show that biliary RFA treatment is a promising adjuvant therapy in patients with unresectable malignant biliary obstruction. The procedure is safe, well tolerated and improves stent patency and survival, even though more studies are warranted. In patients with residual endobiliary adenomatous tissue after endoscopic papillectomy, a significant rate of neoplasia eradication after a single RFA session has been reported, thus favoring this treatment over surgical intervention. In these patients, as well as in those with benign biliary strictures, dedicated probes with a short electrode able to focus the RF current on the short stenosis are needed to expand RFA treatment for these indications.

Image-Guided Thyroid Ablation: Proposal for Standardization of Terminology and Reporting Criteria

Background: Image-guided tumor ablation is commonly performed in clinical practice. Trying to standardize terminology and data collection to enable a more reliable comparison among the different studies, in 2003, a document entitled "Image-Guided Tumor Ablation: Proposal for Standardization of Terms and Reporting Criteria" was published by the International Working Group on Image-Guided Tumor Ablation. Since then, ablations have evolved significantly, with the development of new technology and techniques and applications. This has included benign thyroid nodules, and their ablation has become increasingly accessible, not only among radiologists but also among other specialists involved in thyroid care, including endocrinologists and surgeons. This has resulted in further inhomogeneity in how data are presented and reported among different studies, resulting in a need for standardization to homogenize language and data reporting on the topic. Summary: In February 2018 in Milano, Italy, a meeting involving specialists concerned with minimally invasive treatments of thyroid lesions was organized, and the Italian Working Group on Minimally Invasive Treatments of the Thyroid was founded with the aim of establishing a collaborative network among all clinicians working in this field. The first work of this group is to present a proposal for standardization of terminology and reporting criteria on image-guided ablations to treat benign thyroid nodules. Conclusion: This proposal was drafted with the goal of providing guidance for standardized reporting of results in studies regarding image-guided thyroid ablations. We encourage adoption of this terminology worldwide, anticipating that this will facilitate improved communication and understanding within the field and stimulate further discussion on the topic over the next years.