Dermoscopy diagnosis of cancerous lesions utilizing dual deep learning algorithms via visual and audio (sonification) outputs: Laboratory and prospective observational studies.

BACKGROUND: Early diagnosis of skin cancer lesions by dermoscopy, the gold standard in dermatological imaging, calls for a diagnostic upscale. The aim of the study was to improve the accuracy of dermoscopic skin cancer diagnosis through use of novel deep learning (DL) algorithms. An additional sonification-derived diagnostic layer was added to the visual classification to increase sensitivity. METHODS: Two parallel studies were conducted: a laboratory retrospective study (LABS, n = 482 biopsies) and a non-interventional prospective observational study (OBS, n = 63 biopsies). A training data set of biopsy-verified reports, normal and cancerous skin lesions (n = 3954), were used to develop a DL classifier exploring visual features (System A). The outputs of the classifier were sonified, i.e. data conversion into sound (System B). Derived sound files were analyzed by a second machine learning classifier, either as raw audio (LABS, OBS) or following conversion into spectrograms (LABS) and by image analysis and human heuristics (OBS). The OBS criteria outcomes were System A specificity and System B sensitivity as raw sounds, spectrogram areas or heuristics. FINDINGS: LABS employed dermoscopies, half benign half malignant, and compared the accuracy of Systems A and B. System A algorithm resulted in a ROC AUC of 0.976 (95% CI, 0.965-0.987). Secondary machine learning analysis of raw sound, FFT and Spectrogram ROC curves resulted in AUC's of 0.931 (95% CI 0.881-0.981), 0.90 (95% CI 0.838-0.963) and 0.988 (CI 95% 0.973-1.001), respectively. OBS analysis of raw sound dermoscopies by the secondary machine learning resulted in a ROC AUC of 0.819 (95% CI, 0.7956 to 0.8406). OBS image analysis of AUC for spectrograms displayed a ROC AUC of 0.808 (CI 95% 0.6945 To 0.9208). By applying a heuristic analysis of Systems A and B a sensitivity of 86% and specificity of 91% were derived in the clinical study. INTERPRETATION: Adding a second stage of processing, which includes a deep learning algorithm of sonification and heuristic inspection with machine learning, significantly improves diagnostic accuracy. A combined two-stage system is expected to assist clinical decisions and de-escalate the current trend of over-diagnosis of skin cancer lesions as pathological. FUND: Bostel Technologies. Trial Registration clinicaltrials.gov Identifier: NCT03362138.

Hypersecretion of zymogen granules in the pathogenesis of cystic fibrosis.

In the submandibular saliva of 10 cystic fibrosis subjects and 10 controls the turbidity and elevated calcium, protein, and amylase concentrations of the cystic fibrosis secretions, and precipitation of calcium and phosphate in a ratio consistent with hydroxyapatite have been confirmed. By electron microscopy the centrifuged deposits of the cystic fibrosis saliva were seen to be composed predominantly of round or oval subcellular corpuscles. By comparison with submandibular gland, these corpuscles have been identified as inclusion bodies (spherules) from within zymogen granules. Hydroxyapatite crystals formed on standing in the cystic fibrosis saliva. Polyacrylamide gel disc electrophoresis of the cystic fibrosis centrifuged deposits showed five bands, one of which, band 4, was more prominent in the deposit than in the supernatant gels. Comparisons have been made between these results and other studies and have shown (1) elevated calcium and protein in cystic fibrosis exocrine secretions; (2) simultaneous secretion of calcium and enzymes from salivary glands, stomach, and pancreas; and (3) increased salivary secretion of calcium and protein in response to parasympathomimetic and sympathomimetic drugs. Hypersecretion of calcium-containing zymogen granules is postulated as the cause of obstruction in cystic fibrosis.