BACKGROUND: The introduction of new targeted therapies for RET-altered lung and thyroid cancers (LC/TC) has impacted pathologists\' practice by making genomic testing more relevant. Variations in health systems and treatment access result in distinct clinical challenges and barriers. This study aimed to assess practice gaps and challenges experienced by pathologists involved in the diagnosis of RET-altered LC/TC, including biomarker testing, to inform educational solutions.
METHODS: Pathologists in Germany, Japan, the UK, and US participated in this ethics-approved mixed-methods study, which included interviews and surveys (data collected January-March 2020). Qualitative data was thematically analysed, quantitative data was analysed with chi-square and Kruskal-Wallis H-tests, and both were triangulated.
RESULTS: A total of 107 pathologists took part in this study. Knowledge gaps were reported regarding genomic testing for LC/TC in Japan (79/60%), the UK (73/66%), and the US (53/30%). Skill gaps were reported when selecting genomic biomarker tests to diagnose TC in Japan (79%), the UK (73%) and US (57%) and when performing specific biomarker tests, especially in Japan (82% for RET) and in the UK (75% for RET). Japanese participants (80%) reported uncertainty about what information to share with the multidisciplinary team to ensure optimal patient-centered care. At the time of data collection, pathologists in Japan faced access barriers to using RET biomarker tests: only 28% agreed that there are relevant RET genomic biomarker tests available in Japan, versus 67% to 90% in other countries.
CONCLUSIONS: This study identified areas where pathologists need additional continuing professional development opportunities to enhance their competencies and better support delivery of care to patients with RET-altered lung or thyroid tumours. Addressing identified gaps and improving competencies of pathologists in this field should be emphasised in continuing medical education curricula and through quality improvement initiatives. Strategies deployed on an institutional and health system level should aim to improve interprofessional communication and genetic biomarker testing expertise.

OBJECTIVE: The purpose of this study was to use a computer-aided diagnosis (CAD) system based on the Thyroid Imaging, Reporting, and Data System (TI-RADS) to improve the diagnostic performance of thyroid cancer by analyzing clinical ultrasound imaging data.
METHODS: A retrospective diagnostic study of ultrasound image sets was conducted at five hospitals in China. A CAD system based on TI-RADS was applied in this study, and the diagnostic performance of CAD system was tested through multi-center data. The performance of the CAD system was compared with the consensus of three experienced radiologists. The interobserver agreement for cancer diagnosis was calculated between the CAD system and the consensus of the three experienced radiologists.
RESULTS: The CAD system performed well in the diagnosis of thyroid cancer, with an area under the curve (AUC) value of 0.902 (95% CI: 0.884-0.918), and obtained results similar to those of the three experienced radiologists. The CAD system performed better in the internal test set than in the external test set (AUC: 0.930 vs 0.877, respectively). The performance of the CAD system in the diagnosis of thyroid cancer for nodules of different sizes (<1 cm, 1-2 cm and ≥2 cm) was basically similar (accuracy: 84.6% vs 85% vs 84.2%). The CAD system can recognize 15 ultrasound features of thyroid nodules, most of which reached the level of 3 experienced radiologists (12/15, 85%).
CONCLUSIONS: The CAD system achieved an improved AUC and similar sensitivity and specificity in the diagnosis of thyroid cancer compared with the consensus of experienced radiologists.