Abstract
Background
Helicobacter pylori, a 2 × 1 μm spiral-shaped bacterium, is the most common risk factor for gastric cancer worldwide. Clinically, patients presenting with symptoms of gastritis, routinely undergo gastric biopsies. The following histo-morphological evaluation dictates therapeutic decisions, where antibiotics are used for H. pylori eradication. There is a strong rational to accelerate the detection process of H. pylori on histological specimens, using novel technologies, such as deep learning.
Methods
We designed a deep-learning-based decision support algorithm that can be applied on regular whole slide images of gastric biopsies. In detail, we can detect H. pylori both on Giemsa- and regular H&E stained whole slide images.
Results
With the help of our decision support algorithm, we show an increased sensitivity in a subset of 87 cases that underwent additional PCR- and immunohistochemical testing to define a sensitive ground truth of HP presence. For Giemsa stained sections, the decision support algorithm achieved a sensitivity of 100% compared to 68.4% (microscopic diagnosis), with a tolerable specificity of 66.2% for the decision support algorithm compared to 92.6 (microscopic diagnosis).
Conclusion
Together, we provide the first evidence of a decision support algorithm proving as a sensitive screening option for H. pylori that can potentially aid pathologists to accurately diagnose H. pylori presence on gastric biopsies.
Ardila D, Kiraly AP, Bharadwaj S, Choi B, Reicher JJ, Peng L, Tse D, Etemadi M, Ye W, Corrado G, Naidich DP, Shetty S. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med 2019 May 20;25:954-61 https://www.nature.com/articles/s41591-019-0447-x
Campanella G, Hanna MG, Geneslaw L, Miraflor A, Werneck Krauss Silva V, Busam KJ, Brogi E, Reuter VE, Klimstra DS, Fuchs TJ. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med 2019 Jul 15;25:1301-9 https://www.nature.com/articles/s41591-019-0508-1
AbstractBoth histologic subtypes and tumor mutation burden (TMB) represent important biomarkers in lung cancer, with implications for patient prognosis and treatment decisions. Typically, TMB is evaluated by comprehensive genomic profiling but this requires use of finite tissue specimens and costly, time-consuming laboratory processes. Histologic subtype classification represents an established component of lung adenocarcinoma histopathology, but can be challenging and is associated with substantial inter-pathologist variability. Here we developed a deep learning system to both classify histologic patterns in lung adenocarcinoma and predict TMB status using de-identified Hematoxylin and Eosin (H&E) stained whole slide images. We first trained a convolutional neural network to map histologic features across whole slide images of lung cancer resection specimens. On evaluation using an external data source, this model achieved patch-level area under the receiver operating characteristic curve (AUC) of 0.78–0.98 across nine histologic features. We then integrated the output of this model with clinico-demographic data to develop an interpretable model for TMB classification. The resulting end-to-end system was evaluated on 172 held out cases from TCGA, achieving an AUC of 0.71 (95% CI 0.63–0.80). The benefit of using histologic features in predicting TMB is highlighted by the significant improvement this approach offers over using the clinical features alone (AUC of 0.63 [95% CI 0.53–0.72], p = 0.002). Furthermore, we found that our histologic subtype-based approach achieved performance similar to that of a weakly supervised approach (AUC of 0.72 [95% CI 0.64–0.80]). Together these results underscore that incorporating histologic patterns in biomarker prediction for lung cancer provides informative signals, and that interpretable approaches utilizing these patterns perform comparably with less interpretable, weakly supervised approaches.
Semantic parsing is a challenging and important task which aims to convert a natural language sentence to a logical form. Existing neural semantic parsing methods mainly use <question, logical form> (Q-L) pairs to train a sequence-to-sequence model. However, the amount of existing Q-L labeled data is limited and hard to obtain. We propose an effective method which substantially utilizes labeling information from other tasks to enhance the training of a semantic parser. We design a multi-task learning model to train question type classification, entity mention detection together with question semantic parsing using a shared encoder. We propose a weakly supervised learning method to enhance our multi-task learning model with paraphrase data, based on the idea that the paraphrased questions should have the same logical form and question type information. Finally, we integrate the weakly supervised multi-task learning method to an encoder-decoder framework. Experiments on a newly constructed dataset and ComplexWebQuestions show that our proposed method outperforms state-of-the-art methods which demonstrates the effectiveness and robustness of our method.
Deep learning for sensitive detection of Helicobacter Pylori in gastric biopsies
