A simplified cluster model and a tool adapted for collaborative labeling of lung cancer CT scans.

BACKGROUND AND OBJECTIVE: Lung cancer is the most common type of cancer with a high mortality rate. Early detection using medical imaging is critically important for the long-term survival of the patients. Computer-aided diagnosis (CAD) tools can potentially reduce the number of incorrect interpretations of medical image data by radiologists. Datasets with adequate sample size, annotation, and truth are the dominant factors in developing and training effective CAD algorithms. The objective of this study was to produce a practical approach and a tool for the creation of medical image datasets. METHODS: The proposed model uses the modified maximum transverse diameter approach to mark a putative lung nodule. The modification involves the possibility to use a set of overlapping spheres of appropriate size to approximate the shape of the nodule. The algorithm embedded in the model also groups the marks made by different readers for the same lesion. We used the data of 536 randomly selected patients of Moscow outpatient clinics to create a dataset of standard-dose chest computed tomography (CT) scans utilizing the double-reading approach with arbitration. Six volunteer radiologists independently produced a report for each scan using the proposed model with the main focus on the detection of lesions with sizes ranging from 3 to 30 mm. After this, an arbitrator reviewed their marks and annotations. RESULTS: The maximum transverse diameter approach outperformed the alternative methods (3D box, ellipsoid, and complete outline construction) in a study of 10,000 computer-generated tumor models of different shapes in terms of accuracy and speed of nodule shape approximation. The markup and annotation of the CTLungCa-500 dataset revealed 72 studies containing no lung nodules. The remaining 464 CT scans contained 3151 lesions marked by at least one radiologist: 56%, 14%, and 29% of the lesions were malignant, benign, and non-nodular, respectively. 2887 lesions have the target size of 3-30 mm. Only 70 nodules were uniformly identified by all the six readers. An increase in the number of independent readers providing CT scans interpretations led to an accuracy increase associated with a decrease in agreement. The dataset markup process took three working weeks. CONCLUSIONS: The developed cluster model simplifies the collaborative and crowdsourced creation of image repositories and makes it time-efficient. Our proof-of-concept dataset provides a valuable source of annotated medical imaging data for training CAD algorithms aimed at early detection of lung nodules. The tool and the dataset are publicly available at https://github.com/Center-of-Diagnostics-and-Telemedicine/FAnTom.git and https://mosmed.ai/en/datasets/ct_lungcancer_500/, respectively.

[The future of computer-aided diagnostics in chest computed tomography]. / Perspektivy ispol'zovaniia kompleksnoi komp'iuter-assistirovannoi diagnostiki v otsenke struktur grudnoi kletki.

Recently, more and more attention has been paid to the utility of artificial intelligence in medicine. Radiology differs from other medical specialties with its high digitalization, so most software developers operationalize this area of medicine. The primary condition for machine learning is met because medical diagnostic images have high reproducibility. Today, the most common anatomic area for computed tomography is the thorax, particularly with the widespread lung cancer screening programs using low-dose computed tomography. In this regard, the amount of information that needs to be processed by a radiologist is snowballing. Thus, automatic image analysis will allow more studies to be interpreted. This review is aimed at highlighting the possibilities of machine learning in the chest computed tomography.

Antibacterial and antifungal activity of acyclic and macrocyclic uracil derivatives with quaternized nitrogen atoms in spacers.

The reactions of 1,3-bis(alpha,omega-bromoalkyl)-6-methyluracils with 1,3-bis(alpha,omega-ethylaminoalkyl)-6-methyluracils or 1,3-bis(bromopentyl)thymine with butylamine afforded pyrimidinophanes containing one or two uracil units and nitrogen atoms in bridging polymethylene chains. In some cases individual geometric isomers of pyrimidinophanes differing in the mutual arrangement of the carbonyl and methyl groups at different pyrimidine rings were isolated. Quaternization of the bridging nitrogen atom with o-nitrobenzyl bromide, benzyl bromide, n-decyl bromide gave rise to water-soluble pyrimidinophanes which were evaluated for their antibacterial and antifungal activity. The arrangement of the carbonyl groups in macrocycles doesn't affect the activity. Antibacterial and antifungal activity of pyrimidinophanes increases with the increase of polymethylene N(pyr)-N-chain length and dramatically increases upon the introduction of n-decyl substituent at nitrogen atoms in spacers. Pyrimidinophanes with 5 and 6 methylene groups in N(pyr)-N-chain and n-decyl substituent showed significant bacteriostatic, fungistatic, bactericidal, fungicidal activity which comparable with standard antibacterial and antifungal drugs. Acyclic counterpart demonstrated the highest activity against fungi. Toxicity of more effective pyrimidinophanes was determined for mice and Daphnia magna Straus.

Twisted intramolecular charge transfer states: rotationally resolved fluorescence excitation spectra of 4,4'-dimethylaminobenzonitrile in a molecular beam.

We report the observation at high resolution of seven vibronic bands that appear within approximately 200 cm(-1) of the electronic origin in the S(1)-S(0) fluorescence excitation spectrum of 4,4'-dimethylaminobenzonitrile (DMABN) in a molecular beam. Surprisingly, each band is found to be split into two or more components by a (coordinated) methyl group tunneling motion which significantly complicates the analysis. Despite this fact, high quality [(Observed-Calculated)< or =30 MHz] fits of each of the bands have been obtained, from which the rotational constants, inertial defects, torsion-rotation interaction constants, methyl group torsional barriers, and transition moment orientations of DMABN in both electronic states have been determined. The data show that DMABN is a slightly pyramidalized (approximately 1 degree) but otherwise (heavy-atom) planar molecule in its ground S(0) state, and that its electronically excited S(1) state has both a more pyramidalized (approximately 3 degrees) and twisted (approximately 25 degrees) dimethylamino group. Large reductions in the methyl group torsional barriers also show that the S(1)<--S(0) electronic transition is accompanied by significant charge transfer from the nitrogen atom to the pi* orbitals of the aromatic ring. Thereby established is the participation of all three vibrational coordinates in the dynamics leading to the "anomalous" emissive behavior of DMABN in the condensed phase.