R ecent highest-level evidence is mounting that there is an unequivocal benefit of MRI-targeted biopsies replacing or complementing systematic biopsies for diagnosis of prostate cancer (1-3). Realizing the integral role of MRI in diagnosis of prostate cancer, the Prostate Imaging Reporting and Data System (PI-RADS) continues to be developed (4-7). PI-RADS allows standardization of prostate MRI interpretation, which is a difficult task due to heterogeneous signal changes from benign prostatic hyperplasia, inflammation, and scarring after biopsy mimicking or hiding the appearance of prostate cancer. Even with PI-RADS, the high level of expertise required for accurate interpretation and persistent interobserver variability (8) limit consistency and availability while the demand for prostate MRI interpretation is at unprecedented levels. As convolutional neural networks approach or exceed human performance in natural image analysis (9), they promise to revolutionize computer-aided diagnosis and are increasingly evaluated in prostate MRI (10-15). U-Net is a convolutional neural network architecture optimized for image segmentation. It consists of an encoder and decoder
International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)—a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.
To determine the sensitivity and specificity of HPV16 serology as diagnostic marker for HPV16-driven oropharyngeal squamous cell carcinoma (OPSCC), 214 HNSCC patients from Germany and Italy with fresh-frozen tumor tissues and sera collected before treatment were included in this study. Hundred and twenty cancer cases were from the oropharynx and 94 were from head and neck cancer regions outside the oropharynx (45 oral cavity, 12 hypopharynx and 35 larynx). Serum antibodies to early (E1, E2, E6 and E7) and late (L1) HPV16 proteins were analyzed by multiplex serology and were compared to tumor HPV RNA status as the gold standard. A tumor was defined as HPV-driven in the presence of HPV16 DNA and HPV16 transformation-specific RNA transcript patterns (E6*I, E1 E4 and E1C). Of 120 OPSCC, 66 (55%) were HPV16-driven. HPV16 E6 seropositivity was the best predictor of HPV16-driven OPSCC (diagnostic accuracy 97% [95%CI 92-99%], Cohen's kappa 0.93 [95%CI 0.8-1.0]). Of the 66 HPV-driven OPSCC, 63 were HPV16 E6 seropositive, compared to only one (1.8%) among the 54 non-HPV-driven OPSCC, resulting in a sensitivity of 96% (95%CI 88-98) and a specificity of 98% (95%CI 90-100). Of 94 HNSCC outside the oropharynx, six (6%) were HPV16-driven. In these patients, HPV16 E6 seropositivity had lower sensitivity (50%, 95%CI 19-81), but was highly specific (100%, 95%CI 96-100). In conclusion, HPV16 E6 seropositivity appears to be a highly reliable diagnostic marker for HPV16-driven OPSCC with very high sensitivity and specificity, but might be less sensitive for HPV16-driven HNSCC outside the oropharynx.
As it makes efficient use of available (non-)public and (un-)labeled data, the approach has the potential to become a valuable tool for CNN (pre-)training.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.