A Quantitative Comparison Between Human and Artificial Intelligence in the Detection of Focal Cortical Dysplasia.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Walger Lennart, Bauer Tobias, Kügler David, Schmitz Matthias H, Schuch Fabiane, Arendt Christophe, Baumgartner Tobias, Birkenheier Johannes, Borger Valeri, Endler Christoph, Grau Franziska, Immanuel Christian, Kölle Markus, Kupczyk Patrick, Lakghomi Asadeh, Mackert Sarah, Neuhaus Elisabeth, Nordsiek Julia, Odenthal Anna-Maria, Dague Karmele Olaciregui, Ostermann Laura, Pukropski Jan, Racz Attila, von der Ropp Klaus, Schmeel Frederic Carsten, Schrader Felix, Sitter Aileen, Unruh-Pinheiro Alexander, Voigt Marilia, Vychopen Martin, von Wedel Philip, von Wrede Randi, Attenberger Ulrike, Vatter Hartmut, Philipsen Alexandra, Becker Albert, Reuter Martin, Hattingen Elke, Sander Josemir W, Radbruch Alexander, Surges Rainer, Rüber Theodor
Аннотация
MATERIALS AND METHODS: We prospectively recorded the performance of readers in detecting FCDs using single points and 3-dimensional bounding boxes. We acquired predictions of 3 AI models for the same dataset and compared these to readers. Finally, we analyzed pairwise combinations of readers and models.
RESULTS: Twenty-eight readers, including 20 nonexpert and 5 expert physicians, reviewed 180 cases: 146 subjects with FCD (median age: 25, interquartile range: 18) and 34 healthy control subjects (median age: 43, interquartile range: 19). Nonexpert readers detected 47% (95% confidence interval [CI]: 46, 49) of FCDs, whereas experts detected 68% (95% CI: 65, 71). The 3 AI models detected 32%, 51%, and 72% of FCDs, respectively. The latter, however, also predicted more than 13 false-positive clusters per subject on average. Human performance was improved in the presence of a transmantle sign ( P < 0.001) and cortical thickening ( P < 0.001). In contrast, AI models were sensitive to abnormal gyration ( P < 0.01) or gray-white matter blurring ( P < 0.01). Compared with single experts, expert-expert pairs detected 13% (95% CI: 9, 18) more FCDs ( P < 0.001). All AI models increased expert detection rates by up to 19% (95% CI: 15, 24) ( P < 0.001). Nonexpert+AI pairs could still outperform single experts by up to 13% (95% CI: 10, 17).
CONCLUSIONS: This study pioneers the comparative evaluation of humans and AI for FCD lesion detection. It shows that AI and human predictions differ, especially for certain MRI features of FCD, and, thus, how AI may complement the diagnostic workup.