Noninferiority of Artificial Intelligence-Assisted Analysis of Ki-67 and Estrogen/Progesterone Receptor in Breast Cancer Routine Diagnostics.

Image analysis assistance with artificial intelligence (AI) has become one of the great promises over recent years in pathology, with many scientific studies being published each year. Nonetheless, and perhaps surprisingly, only few image AI systems are already in routine clinical use. A major reason for this is the missing validation of the robustness of many AI systems: beyond a narrow context, the large variability in digital images due to differences in preanalytical laboratory procedures, staining procedures, and scanners can be challenging for the subsequent image analysis. Resulting faulty AI analysis may bias the pathologist and contribute to incorrect diagnoses and, therefore, may lead to inappropriate therapy or prognosis. In this study, a pretrained AI assistance tool for the quantification of Ki-67, estrogen receptor (ER), and progesterone receptor (PR) in breast cancer was evaluated within a realistic study set representative of clinical routine on a total of 204 slides (72 Ki-67, 66 ER, and 66 PR slides). This represents the cohort with the largest image variance for AI tool evaluation to date, including 3 staining systems, 5 whole-slide scanners, and 1 microscope camera. These routine cases were collected without manual preselection and analyzed by 10 participant pathologists from 8 sites. Agreement rates for individual pathologists were found to be 87.6% for Ki-67 and 89.4% for ER/PR, respectively, between scoring with and without the assistance of the AI tool regarding clinical categories. Individual AI analysis results were confirmed by the majority of pathologists in 95.8% of Ki-67 cases and 93.2% of ER/PR cases. The statistical analysis provides evidence for high interobserver variance between pathologists (Krippendorff's α, 0.69) in conventional immunohistochemical quantification. Pathologist agreement increased slightly when using AI support (Krippendorff α, 0.72). Agreement rates of pathologist scores with and without AI assistance provide evidence for the reliability of immunohistochemical scoring with the support of the investigated AI tool under a large number of environmental variables that influence the quality of the diagnosed tissue images.

A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists.

Onychomycosis is common. Diagnosis can be confirmed by various methods; a commonly used method is the histological examination of nail clippings. A deep learning system was developed and its diagnostic accuracy compared with that of human experts. A dataset with annotations for fungal elements was used to train an artificial intelligence (AI) model. In a second dataset (n=199) the diagnostic accuracy of the AI was compared with that of dermatopathologists. The results show a non-inferiority of the deep learning system to that of analogue diagnosis (non-inferiority margin 5%) with respect to specificity and the area under the receiver operating characteristic curve (AUC). The AI achieved an AUC of 0.981. One limitation of this system is the need for a large number of training images. The AI had difficulty recognizing spores and confused serum or aggregated bacteria with fungal elements. Use of this deep learning system in dermatopathology routine might help to diagnose onychomycosis more efficiently.

Synaptic tagging, evaluation of memories, and the distal reward problem.

Long-term synaptic plasticity exhibits distinct phases. The synaptic tagging hypothesis suggests an early phase in which synapses are prepared, or "tagged," for protein capture, and a late phase in which those proteins are integrated into the synapses to achieve memory consolidation. The synapse specificity of the tags is consistent with conventional neural network models of associative memory. Memory consolidation through protein synthesis, however, is neuron specific, and its functional role in those models has not been assessed. Here, using a theoretical network model, we test the tagging hypothesis on its potential to prolong memory lifetimes in an online-learning paradigm. We find that protein synthesis, though not synapse specific, prolongs memory lifetimes if it is used to evaluate memory items on a cellular level. In our model we assume that only "important" memory items evoke protein synthesis such that these become more stable than "unimportant" items, which do not evoke protein synthesis. The network model comprises an equilibrium distribution of synaptic states that is very susceptible to the storage of new items: Most synapses are in a state in which they are plastic and can be changed easily, whereas only those synapses that are essential for the retrieval of the important memory items are in the stable late phase. The model can solve the distal reward problem, where the initial exposure of a memory item and its evaluation are temporally separated. Synaptic tagging hence provides a viable mechanism to consolidate and evaluate memories on a synaptic basis.