ABSTRACT
Artificial intelligence's (AI) emergence in radiology elicits both excitement and uncertainty. AI holds promise for improving radiology with regards to clinical practice, education, and research opportunities. Yet, AI systems are trained on select datasets that can contain bias and inaccuracies. Radiologists must understand these limitations and engage with AI developers at every step of the process - from algorithm initiation and design to development and implementation - to maximize benefit and minimize harm that can be enabled by this technology.
Subject(s)
Artificial Intelligence , Radiology , Humans , Radiology/methods , Algorithms , Diagnostic Imaging/methodsABSTRACT
This manuscript is a collaborative, multi-institutional effort by members of the Society of Abdominal Radiology Uterine and Ovarian Cancer Disease Focus Panel and the European Society of Urogenital Radiology Women Pelvic Imaging working group. The manuscript reviews the key role radiologists play at tumor board and highlights key imaging findings that guide management decisions in patients with the most common gynecologic malignancies including ovarian cancer, cervical cancer, and endometrial cancer.
Subject(s)
Endometrial Neoplasms , Genital Neoplasms, Female , Ovarian Neoplasms , Uterine Cervical Neoplasms , Female , Humans , RadiologistsABSTRACT
PURPOSE: To determine the clinical and ultrasound features of dermoid-associated adnexal torsion. METHODS: Forty-four patients with at least one dermoid and ultrasound ≤ 30 days of surgery were retrospectively reviewed by three radiologists. Ultrasound and clinical findings were compared to intra-operative findings using Fisher's exact test or Mann-Whitney test with p < 0.05 to determine statistical significance.Please check and confirm that the authors and their respective affiliations have been correctly identified and amend if necessary.Correct. No edit RESULTS: Twenty patients had torsion, while 24 patients did not. Patients with dermoid-associated torsion were more likely to present to emergency department (ED) (100% vs 13%; p < 0.001) and have acute unilateral pelvic pain (100% vs 42%; p < 0.001). On ultrasound, patients with torsion had larger dermoids (median largest dimension 9.0 cm (IQR 7.7-11.1) vs 6.0 cm (IQR 4.4-7.5); p < 0.001), displaced dermoid anterior or superior to the uterus (59% vs 21%; p = 0.016), and ipsilateral adnexal fluid (41% vs 4%; p = 0.003). Displaced dermoid and ipsilateral adnexal fluid had substantial (kappa = 0.72) and moderate inter-rater agreement (kappa = 0.49), respectively. The combination of ED presentation and each statistically significant ultrasound feature (dermoid size ≥ 5.0 cm, displaced dermoid, and ipsilateral adnexal fluid) yielded high specificity and positive predictive value (ranging from 93-100% to 92-100%, respectively). The combination of ED presentation and dermoid size ≥ 5.0 cm yielded the highest sensitivity, negative predicative value, and accuracy (100%, 100%, and 96%, respectively).Please check and confirm whether the edit made to the article title is in order.Looks great. No edits. Thank you! CONCLUSION: Although the diagnosis of adnexal torsion in the presence of an ovarian dermoid is traditionally challenging, the combination of ED presentation and ultrasound features increase diagnostic confidence of dermoid-associated adnexal torsion.
