Background. Ovarian heterotopias are quite successfully diagnosed with ultrasound examinations. Considering the high risk of spread of the disease, as well as reproductive consequences (infertility, pelvic adhesive processes, chronic pelvic pain syndrome, dysmenorrhea), early differential diagnosis of endometrioid cysts and, accordingly, early initiation of treatment are of particular importance.
Objective: to combine ultrasound criteria using 3D visualization and the content of biomarkers to verify stage 1–2 endometrioid ovarian cysts.
Material and methods. In 59 infertile women with endometrioid ovarian cysts, in the dynamics of the menstrual cycle, ultrasound examinations were performed using Acuson S2000 (Siemens, Germany) and Voluson E8 (General Electric, USA) with the possibility of Doppler measurements and three-dimensional reconstruction of tissue images. Also, in laboratories “Invitro”, “Hemotest”, “Nauka” (Samara, Russia) the biomarkers were determined: interleukins IL-1β, IL-6, cancer antigen 125 (CA-125), human epididymis protein 4 (HE4) and the index by Risk of Ovarian Malignancy Algorithm (ROMA). The control group included 195 fertile women of reproductive age. In patients with endometrioid cysts, the diagnosis was subsequently confirmed morphologically.
Results. Small unilateral and bilateral ovarian cysts corresponding to stage 1–2 endometriosis by revised American Fertility Society classification (rAFS) were clearly differentiated in 56 (94.9%) patients, in 3 (5.4%) of them the ultrasound result was questionable. In 48 (81.4%) women the lesion was unilateral and in 11 (18.6%) it was bilateral. The structure of cystic formations in all cases was hypoechoic, heterogeneous, in 36 (61.0%) cases it was finely cellular, without blood flow.
Conclusion. Ovarian endometriomas in “gray scale” are round formations of reduced echogenicity and fine suspension, with an even, clear contour, not fused with the surrounding tissues, avascular, changing size depending on menstrual cycle phase. An ovarian mass may have a capsule with locus signals on Doppler. The sensitivity of ultrasound examination in “gray scale” in the presence of an endometrioid cyst is 94.6%.

Background. Gamartoma occupies a special place among solitary lung masses not requiring active surgical tactics: structural heterogeneity due to inclusions of fat density and calcinates presents an opportunity to identify pathognomonic computed tomographic (CT) signs. However, their absence in conjunction with CT picture inherent in malignant neoplasms can cause biopsies and surgical interventions that are not necessary according to the results of histologic examination.
Objective: to perform a cohort retrospective analysis of pulmonary hamartoma CT semiotics.
Маterial and methods. We analyzed 142 cases of lung hamartomas detected at the Saint Petersburg Research Institute of Phthisiopulmonology from 2013 to 2023, confirmed histologically or with a follow-up period of more than 600 days, without endobronchial location and other foci/formations in the lungs, without contrast enhancement evaluation.
Results. The results of data statistical analysis of patients with pulmonary hamartoma with distribution by gender and age were described. The occurrence rate was established for such hamartoma CT features as mass type, contour features, changes in the surrounding lung tissue, the largest diameter, density, calcination type with examples on CT images. Localizations of hamartomas in relation to the lung, its lobes and segments were considered. Four hamartoma clusters depending on fat and calcination combination in the structure were identified and illustrated. The size distribution of hamartomas from each cluster within the given ranges was also presented.
Conclusion. Lung hamartomas are solid-type masses without preferential localization in lung segments, with the possibility of detection at any age. In a significant proportion of cases (43.7%) hamartomas did not have any structural features, which allow, according to CT data, to convincingly classify them as benign masses and avoid surgical resection. Only in 12% of cases hamartomas had structural changes considered highly pathognomonic for their classification as benign masses.

Objective: comparative evaluation of output data of a set of trained convolutional neural network (CNN) models and interpretation of pathological changes in lumbar spine by radiologists during magnetic resonance imaging.
Material and methods. More than 12,000 anonymized archives were collected to generate training and test neural network datasets from patients aged over 18 years. Each archive consisted of a set of programs in two planes containing T2-TSE, T1-TSE and T2 sequences with fat suppression program. Subsequently, the selected studies were tagged in two steps, directly consisting of manual tagging and its validation by experts. CNN training was performed separately for normal analysis, qualitative detection of individual pathological changes, and quantitative analysis. The accuracy of the models was verified by comparing the protocols of five radiologists and the output of CNN models in two steps. The first, intermediate stage evaluated the accuracy of the neural networks in detecting disc bulges, protrusions and extrusions, spinal canal stenosis, lateral stenosis, foraminal stenosis, spondylolisthesis and facet joint arthrosis. In the final stage, in addition to the pathologies considered in the intermediate one, the accuracy of detecting degenerative changes of the occlusive plates, synovitis of intervertebral joints, intervertebral discs degeneration, osteophytes, transitional vertebrae, hypertrophy of yellow ligaments and Schmorl’s hernia was tested. The reference value for all pathological changes considered in this paper was determined by majority vote and, in case of disagreement, by an external radiologist. The radiologists’ interpretations were then compared with those of the trained model.
Results. The artificial intelligence (AI) showed comparable sensitivity and specificity values compared to the reference result in a group of experienced radiologists for binary classification (presence/absence) of individual lumbosacral spine degenerative changes. The sensitivity and specificity of AI results were 0.88 and 0.97 for extrusions, 0.81 and 0.94 for protrusions, 0.87 and 0.98 for central stenosis, 0.83 and 0.85 for lateral stenosis, 0.92 and 0.84 for foraminal stenosis, 0.85 and 0.5 for osteoarthritis, 0.73 and 0.96 for occlusive plates degeneration, 0.85 and 0.84 for intervertebral joint synovitis, 0.91 and 0.88 for osteophytes, 0.93 and 0.72 for intervertebral disc degeneration, 1.0 and 1.0 for transitional vertebrae, 0.8 and 1.0 for spondylolisthesis, 0.67 and 0.99 for yellow ligament hypertrophy, and 0.75 and 1.0 for Schmorl’s hernia, respectively. The accuracy of quantitative size characterization of lumbosacral spine protrusions and extrusions showed unsatisfactory results, but improvements in the quality of determination of these parameters are planned in future work.
Conclusion. AI models showed comparable performance to expert radiologists in detecting lumbosacral spine degenerative changes. Consistent improvement of CNN models based on comparative evaluation with radiologists improves the sensitivity and specificity of pathologic change detection.

Determining the nature of nodular alternations in the lungs still remains an urgent problem in oncology, pulmonology, and radiology. In some cases, the final diagnosis can be established only on the basis of studying the material obtained during bronchobiopsy, transthoracic biopsy, and surgical treatment. Bronchobiopsy is the first stage of minimally invasive diagnostics towards detecting the nature of nodular changes in the lung tissue, the effectiveness of which depends on preliminary navigation to the region of interest using computed tomography (CT). The article presents five clinical cases demonstrating the use of CT navigation technology for performing bronchobiopsy in patients with peripheral pulmonary nodules.

The article presents the clinical observation of a patient born in 1965, who was examined and treated at the Russian Scientific Center of Roentgenoradiology for tumor of anterior bladder wall detected in May 2023 according to the results of radiation diagnostic methods (ultrasound, computed tomography, magnetic resonance imaging). Analysis of biopsy material obtained during cystoscopy revealed a highly differentiated mucinous urachal adenocarcinoma. Based on the diagnosis of malignant neoplasm of primary urinary tract (urachus) pT3N0M0 stage II, the surgical treatment was proposed. In June 2023, the Bricker procedure was performed: laparoscopic anterior pelvic exenteration with formation of intestinal reservoir. Control examination 3 months after showed no progression of the disease. Asymptomatic development of urachal carcinoma in early stages, peculiarities of its location in pelvic cavity and propensity to metastasis, as well as the rarity of such neoplasm indicate the need for earlier and more accurate verification of the diagnosis. This clinical case demonstrates characteristic clinical and imaging features of urachal adenocarcinoma, which may help radiologists, oncologists, and urologists in making diagnosis and choosing correct treatment tactics.