Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220783959> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4220783959 abstract "Abstract Diagnostic histopathology is facing increasing demands due to aging populations and expanding healthcare programs. Semi-automated diagnostic systems employing deep learning methods are one approach to alleviate this pressure, with promising results for many routine diagnostic procedures. However, one major issue with deep learning approaches is their lack of interpretability—after adequate training they perform their assigned tasks admirably, but do not explain how they reach their conclusions. Knowledge of how a given method performs its task with high sensitivity and specificity would be advantageous to understand the key features responsible for diagnosis, and should in turn allow fine-tuning of deep learning approaches. This paper presents a deep learning-based system for carcinoma detection in whole slide images of prostate core biopsies, achieving state-of-the-art performance; 100% area under curve and sensitivity of 0.978 for 8 detected false positives on average per slide. Furthermore, we investigated various methods to extract the key features used by the neural network for classification. Of these, the technique called occlusion, adapted to whole slide images, analyzes the sensitivity of the detection system to changes in the input images. This technique produces heatmaps indicating which parts of the image have the strongest impact on the system’s output that a histopathologist can examine to identify the network’s reasoning behind a given classification. Reassuringly, the heatmaps identified several prevailing histomorphological features characterizing carcinoma, e.g. single-layered epithelium, presence of small lumina, and hyperchromatic nuclei with halos. A convincing finding was the recognition of their mimickers in non-neoplastic tissue. The results show that the neural network approach to recognize prostatic cancer is similar to that taken by a human pathologist at medium optical resolution. The use of explain-ability heatmaps provides added value for automated digital pathology to analyze and fine-tune deep learning systems, and improves trust in computer-based decisions." @default.
- W4220783959 created "2022-04-03" @default.
- W4220783959 creator A5001632758 @default.
- W4220783959 creator A5018373101 @default.
- W4220783959 creator A5055695231 @default.
- W4220783959 creator A5073500944 @default.
- W4220783959 creator A5074091743 @default.
- W4220783959 creator A5082160514 @default.
- W4220783959 date "2022-04-01" @default.
- W4220783959 modified "2023-10-01" @default.
- W4220783959 title "Shedding Light on the Black Box of a Neural Network Used to Detect Prostate Cancer in Whole Slide Images by Occlusion-Based Explainability" @default.
- W4220783959 cites W1849277567 @default.
- W4220783959 cites W1977653087 @default.
- W4220783959 cites W2282821441 @default.
- W4220783959 cites W2401520370 @default.
- W4220783959 cites W2761668583 @default.
- W4220783959 cites W2801876365 @default.
- W4220783959 cites W2945574311 @default.
- W4220783959 cites W2956228567 @default.
- W4220783959 cites W2962081597 @default.
- W4220783959 cites W2964756323 @default.
- W4220783959 cites W2982406227 @default.
- W4220783959 cites W2999399991 @default.
- W4220783959 cites W3020916919 @default.
- W4220783959 cites W3045168954 @default.
- W4220783959 cites W3097598935 @default.
- W4220783959 cites W3120894151 @default.
- W4220783959 cites W3160261825 @default.
- W4220783959 cites W3196551901 @default.
- W4220783959 doi "https://doi.org/10.1101/2022.03.31.486599" @default.
- W4220783959 hasPublicationYear "2022" @default.
- W4220783959 type Work @default.
- W4220783959 citedByCount "2" @default.
- W4220783959 countsByYear W42207839592023 @default.
- W4220783959 crossrefType "posted-content" @default.
- W4220783959 hasAuthorship W4220783959A5001632758 @default.
- W4220783959 hasAuthorship W4220783959A5018373101 @default.
- W4220783959 hasAuthorship W4220783959A5055695231 @default.
- W4220783959 hasAuthorship W4220783959A5073500944 @default.
- W4220783959 hasAuthorship W4220783959A5074091743 @default.
- W4220783959 hasAuthorship W4220783959A5082160514 @default.
- W4220783959 hasBestOaLocation W42207839591 @default.
- W4220783959 hasConcept C108583219 @default.
- W4220783959 hasConcept C112789634 @default.
- W4220783959 hasConcept C119857082 @default.
- W4220783959 hasConcept C127413603 @default.
- W4220783959 hasConcept C153180895 @default.
- W4220783959 hasConcept C154945302 @default.
- W4220783959 hasConcept C21200559 @default.
- W4220783959 hasConcept C24326235 @default.
- W4220783959 hasConcept C2781067378 @default.
- W4220783959 hasConcept C41008148 @default.
- W4220783959 hasConcept C50644808 @default.
- W4220783959 hasConcept C64869954 @default.
- W4220783959 hasConcept C81363708 @default.
- W4220783959 hasConcept C94966114 @default.
- W4220783959 hasConceptScore W4220783959C108583219 @default.
- W4220783959 hasConceptScore W4220783959C112789634 @default.
- W4220783959 hasConceptScore W4220783959C119857082 @default.
- W4220783959 hasConceptScore W4220783959C127413603 @default.
- W4220783959 hasConceptScore W4220783959C153180895 @default.
- W4220783959 hasConceptScore W4220783959C154945302 @default.
- W4220783959 hasConceptScore W4220783959C21200559 @default.
- W4220783959 hasConceptScore W4220783959C24326235 @default.
- W4220783959 hasConceptScore W4220783959C2781067378 @default.
- W4220783959 hasConceptScore W4220783959C41008148 @default.
- W4220783959 hasConceptScore W4220783959C50644808 @default.
- W4220783959 hasConceptScore W4220783959C64869954 @default.
- W4220783959 hasConceptScore W4220783959C81363708 @default.
- W4220783959 hasConceptScore W4220783959C94966114 @default.
- W4220783959 hasLocation W42207839591 @default.
- W4220783959 hasOpenAccess W4220783959 @default.
- W4220783959 hasPrimaryLocation W42207839591 @default.
- W4220783959 hasRelatedWork W3003526064 @default.
- W4220783959 hasRelatedWork W3006943036 @default.
- W4220783959 hasRelatedWork W3021357056 @default.
- W4220783959 hasRelatedWork W3037743169 @default.
- W4220783959 hasRelatedWork W3134763859 @default.
- W4220783959 hasRelatedWork W4213225422 @default.
- W4220783959 hasRelatedWork W4220783959 @default.
- W4220783959 hasRelatedWork W4287900725 @default.
- W4220783959 hasRelatedWork W4299487748 @default.
- W4220783959 hasRelatedWork W4310880831 @default.
- W4220783959 isParatext "false" @default.
- W4220783959 isRetracted "false" @default.
- W4220783959 workType "article" @default.