Artificial Intelligence for Pre-operative Diagnosis of Malignant Thyroid Nodules Based on Sonographic Features and Cytology Category.

BACKGROUND: Current diagnosis and classification of thyroid nodules are susceptible to subjective factors. Despite widespread use of ultrasonography (USG) and fine needle aspiration cytology (FNAC) to assess thyroid nodules, the interpretation of results is nuanced and requires specialist endocrine surgery input. Using readily available pre-operative data, the aims of this study were to develop artificial intelligence (AI) models to classify nodules into likely benign or malignant and to compare the diagnostic performance of the models. METHODS: Patients undergoing surgery for thyroid nodules between 2010 and 2020 were recruited from our institution's database into training and testing groups. Demographics, serum TSH level, cytology, ultrasonography features and histopathology data were extracted. The training group USG images were re-reviewed by a study radiologist experienced in thyroid USG, who reported the relevant features and supplemented with data extracted from existing reports to reduce sampling bias. Testing group USG features were extracted solely from existing reports to reflect real-life practice of a non-thyroid specialist. We developed four AI models based on classification algorithms (k-Nearest Neighbour, Support Vector Machine, Decision Tree, Naïve Bayes) and evaluated their diagnostic performance of thyroid malignancy. RESULTS: In the training group (n = 857), 75% were female and 27% of cases were malignant. The testing group (n = 198) consisted of 77% females and 17% malignant cases. Mean age was 54.7 ± 16.2 years for the training group and 50.1 ± 17.4 years for the testing group. Following validation with the testing group, support vector machine classifier was found to perform best in predicting final histopathology with an accuracy of 89%, sensitivity 89%, specificity 83%, F-score 94% and AUROC 0.86. CONCLUSION: We have developed a first of its kind, pilot AI model that can accurately predict malignancy in thyroid nodules using USG features, FNAC, demographics and serum TSH. There is potential for a model like this to be used as a decision support tool in under-resourced areas as well as by non-thyroid specialists.

Preoperative serum calcitonin may improve initial surgery for medullary thyroid cancer in patients with indeterminate cytology.

BACKGROUND: Medullary thyroid cancer (MTC) is rare, with poorer outcomes than differentiated thyroid cancer. We aimed to identify areas for improvement in the pre-operative evaluation of patients with possible MTC in a high-volume endocrine surgery unit in accordance with current practice guidelines. We hypothesised that the selective use of serum calcitonin (sCT) as a biomarker for possible MTC could guide the extent of initial surgical management. METHODS: We recruited MTC patients between 2000 and 2020 from the Monash University Endocrine Surgery Unit database. Demographics, tumour characteristics, pre-operative evaluation, operative management, and outcomes were analysed. RESULTS: Of 1454 thyroid cancer patients, 43 (3%) had MTC. Pre-operatively, 36 (84%) patients with MTC confirmed on cytology (28, 65%), elevated sCT (6, 14%) or RET mutation (2, 4%). Of these 36 patients, 31 (86%) had optimal extent of thyroidectomy and lymph node dissection (LND). Five (14%) had less than total thyroidectomy due to nerve injury. Thirty-four patients had compartmental LND. In the 12 (27%) patients with indeterminate or non-diagnostic cytology, 5 had elevated sCT and were managed as above. None of the remaining seven had LND, thus potentially suboptimal surgery. CONCLUSION: Our findings reflect the rarity of MTC, and the challenges of pre-operative diagnosis. The addition of sCT may improve surgical planning in patients with indeterminate cytology.

Challenges in diagnosis and management of a spiradenocarcinoma: a comprehensive literature review.

BACKGROUND: Spiradenocarcinoma is a rare skin adnexal neoplasm that may behave aggressively. It is often associated with a benign slow-growing spiradenoma that has undergone malignant transformation. Given the paucity of cases in the literature, there is a lack of consensus on treatment. METHODS: The terms 'malignant spiradenoma' or 'spiradenocarcinoma' were systematically used to search the PubMed, MEDLINE and Google Scholar databases. A total of 182 cases of spiradenocarcinoma were identified as eligible for this comprehensive literature review. RESULTS: Spiradenocarcinoma was commoner in older age and Caucasian race. In most cases, surgical excision for local disease is the mainstay of treatment. Lymph node dissection is usually reserved for those with suspected or confirmed lymph node metastases. High rates of local recurrence (20.8%), metastasis (37.4%) and mortality (19.1%) were identified, prompting some authors to suggest regular follow up including chest X-rays and liver function tests. CONCLUSIONS: Patients with spiradenocarcinoma may benefit from a magnetic resonance imaging and fluorodeoxyglucose-positron emission tomography/computed tomography to establish the extent of disease. We recommend wide local excision as the treatment of choice to achieve surgical margins of ≥1 cm, with node resection to be determined on a case-to-case basis. Regular follow up is important given the high rate of local recurrence, metastasis and mortality. This should include an examination of the regional lymph nodes. Further research is required to refine an evidence-based approach to spiradenocarcinoma.