The overall incidence of pseudoprogression is 6% and less than 10% in subgroups according to the definition of pseudoprogression, cancer type, and drug type. BackgroundImmune checkpoint inhibitors (ICIs) have been increasingly used in cancer treatment, and a subset of patients undergo pseudoprogression. Recognizing the incidence of pseudoprogression is ...

Using direct radiologic image inputs, two large language models, GPT-4V and Gemini Pro Vision, improved in diagnostic accuracy with increasing temperature settings; although GPT-4V slightly underperformed compared with radiologists, it nonetheless demonstrated promising potential as a supportive tool in diagnostic decision-making.

BACKGROUND AND PURPOSE: Ultrasound has become widely accepted as the first imaging technique used for the assessment of cervical lymph node metastasis in patients with papillary thyroid cancer. In this systematic review and meta-analysis, we evaluate the performance of CT for the preoperative diagnosis of cervical lymph node metastasis in patients with papillary thyroid cancer compared with ultrasound. MATERIALS AND METHODS: Ovid-MEDLINE and EMBASE data bases were searched for studies regarding the use of CT to diagnose cervical lymph node metastasis. The diagnostic performance of CT, ultrasound, and combined CT/ultrasound was assessed by using level-by-level and patient-based analyses. We also performed meta-analyses on the basis of the central and lateral neck levels. RESULTS: Nine eligible studies, including a total sample size of 1691 patients, were included. CT showed a summary sensitivity of 62% (95% CI, 52%–70%) and specificity of 87% (95% CI, 80%–92%) for diagnosing cervical lymph node metastasis when using level-by-level analysis. There was a positive correlation between the sensitivity and the false-positive rate (correlation coefficient, 0.807) because of the threshold effect. The summary sensitivity of combined CT/ultrasound (69%; 95% CI, 61%–77%) was significantly higher than ultrasound (51%; 95% CI, 42%–60%), though the summary specificity did not differ. CONCLUSIONS: The diagnostic performances of CT and ultrasound are similar, though CT and ultrasound combined are superior to ultrasound only. CT may be used as a complementary diagnostic method in addition to ultrasound for diagnosing cervical lymph node metastasis in patients with papillary thyroid cancer.

Background The diagnostic performance and unnecessary biopsy rates for evaluation of thyroid nodules varies among the current society guidelines. We hypothesized that diagnostic performance and unnecessary biopsy rates of different guidelines are largely determined by different thyroid size thresholds used as cutoff values that determine when to biopsy a thyroid nodule. Purpose To compare the malignancy risk, diagnostic performance, and unnecessary biopsy rates of three guidelines and evaluate the changes according to the nodule size cutoff for biopsy. Materials and Methods This retrospective study included 3323 consecutive thyroid nodules from 3190 patients between January 2013 and December 2013. US features were reviewed according to the American Thyroid Association (ATA), Korean Thyroid Association/Korean Society of Thyroid Radiology (KTA/KSThR), and American College of Radiology (ACR) guidelines. The diagnostic performance and unnecessary biopsy rates were calculated. The size cutoff of ATA and KTA/KSThR guidelines was varied and diagnostic performance and unnecessary biopsy rates were calculated and compared by using the generalized estimating equations method. Results A total of 856 (25.8%) thyroid nodules were diagnosed as malignant after surgical excision or biopsy. The highest sensitivity was observed with the KTA/KSThR guideline (93.5% [300 of 321]), followed by the ATA (92.5% [297 of 321]) and ACR guidelines (60.1% [193 of 321]). The highest specificity (75.2% [1216 of 1617], P < .001) with lowest unnecessary biopsy rate (20.7% [401 of 1938]) was observed with the ACR guideline. When the low-suspicion category in the ATA guideline modeled 2.5 cm instead of 1.5 cm as the size for biopsy, the unnecessary biopsy rate decreased to 43.6% (845 of 1938, 2.5-cm cutoff) compared with 55.1% (1068 of 1938, 1.5-cm cutoff) (P < .001). For the KTA/KSThR guidelines, the unnecessary biopsy rate decreased to 36.4% (706 of 1938, 2.5-cm cutoff) compared with 59.5% (1153 of 1938, 1.5-cm cutoff) (P < .001). Conclusion The diagnostic performance and unnecessary biopsy rates of the American Thyroid Association and the Korean Thyroid Association/Korean Society of Thyroid Radiology guidelines are strongly influenced by nodule size cutoff. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Foley in this issue.

Park SH, et al. Korean J Radiol. 2024 Oct;25(10):865-868. https://doi.org/10.3348/kjr.2024.0843

Large language models accurately answered New England Journal of Medicine Image Challenge cases using radiologic inputs, outperforming a medical student; however, their accuracy decreased with shorter text lengths, regardless of image inputs.