1 January 2023 in Vestnik of Saint Petersburg University. Medicine
AUAstana Medical University
Astana Medical University
SUSt. Petersburg State University
St. Petersburg State University
SHSt. Petersburg City Mariinsky Hospital
St. Petersburg City Mariinsky Hospital
IUI. M. Sechenov First Moscow State Medical University (Sechenov University)
I. M. Sechenov First Moscow State Medical University (Sechenov University)
+4
This review examines the current methodologies employed in utilizing artificial intelligence for the identification and classification of prostate cancer using magnetic resonance imaging data. It outlines the volume of data utilized and highlights the most commonly sought-after sequences employed for training neural networks. The review further presents the accuracy metrics of the neural networks analyzed, accompanied by a succinct explanation of each metric. Furthermore, the review pinpoints the limitations associated with contemporary neural networks devised for the detection and classification of prostate cancer using magnetic resonance imaging data, as well as the challenges encountered during their creation and implementation.In summary, this comprehensive analysis delves into the existing approaches in leveraging artificial intelligence for prostate cancer detection and stratification through magnetic resonance imaging data. It addresses the data scale and preferred magnetic resonance imaging sequences employed for neural network training. The review provides a breakdown of accuracy indicators for the neural networks evaluated, elucidating their respective capabilities. Moreover, the review identifies the drawbacks associated with current neural network models developed for prostate cancer detection and stratification via magnetic resonance imaging data, while also recognizing the complexities involved in their development and practical application.
30 September 2026 in Russian Military Medical Academy Reports
ГРГафиатулин Марат Риатович
Гафиатулин Марат Риатович
+18
Rhombencephalosynapsis is a rare anomaly of cerebellar development that remains a diagnostic challenge for radiologists. Important unresolved issues include its true prevalence, frequent diagnostic misses in adult patients with predominant psychiatric symptoms, and the spectrum of characteristic associated findings on magnetic resonance imaging. Based on an analysis of 41 publications (summarizing 72 cases), the article systematizes the most common concomitant anomalies: agenesis of the septum pellucidum (46%), hydrocephalus (39%), and corpus callosum anomalies (37.5%). Magnetic resonance imaging remains the key method for diagnosing cerebellar anomalies, as emphasized by the case of a 35-year-old patient with treatment-resistant psychiatric disorder in whom rhombencephalosynapsis was missed on initial magnetic resonance imaging and detected only on targeted repeat brain magnetic resonance imaging. The article briefly presents available information on the prevalence and genetic basis of rhombencephalosynapsis; magnetic resonance imaging images of morphological brain changes analyzed in published data are presented as illustrations, and our own observation is described. The authors emphasize the importance of increasing radiologists’ awareness of rhombencephalosynapsis to minimize diagnostic errors in children and adults, and therefore developed recommendations for analyzing brain magnetic resonance imaging images when detecting the above-described patterns.
11 November 2023 in Medicine: theory and practice
МВМаксимович Черемисин Владимир
Максимович Черемисин Владимир
ДИДмитрий Иванович Ивашкин
БМБорис Георгиевич Макаренко
Борис Георгиевич Макаренко
Целью исследования явилось сравнение КТ-показателей саркопении у пациентов с онкологическими заболеваниями и без них. Материалы и методы. Были изучены и выбраны два основных показателя саркопении, SMI (скелетно-мышечный индекс) и PMI (мышечный индекс поясничной мышцы). Они оценивались по МСКТ брюшной полости на уровне LIIIпозвонка. Результаты и заключение. При сравнении данных показателей было обнаружено, что при использовании конкретных пороговых значений только SMI-критерий показал себястатистически более достоверным, чем PMI-критерий, поэтому он предпочтительнее к использованию в диагностике саркопении. Поскольку нет единых стандартизированных пороговых значений саркопении, нельзя однозначно заявлять о несостоятельности PMI-критерия как такового. Данный результат не доказывает невозможность использования PMI-критерия. Полученные показатели свидетельствуют о целесообразности дальнейшего изучения феномена саркопении у онкологических пациентов с большой выборкой. В настоящее время не существует всеми признанного метода лучевой диагностики саркопении. Диагностика саркопении с помощью компьютерной томографии (КТ), бесспорно, является важнейшим этапом для уменьшения осложнений и улучшения качества лечения как онкологических больных, так и пациентов другого профиля. Необходим дальнейший поиск КТ-показателей и их пороговых значений для точной диагностики саркопении. The aim of the study was to compare CT indicators of sarcopenia in patients with and without cancer. Materials and methods. Two main indicators of sarcopenia, SMI (skeletal muscle index) and PMI (m. Psoas muscle index) were selected and studied. They were assessed using MSCT of the abdominal cavity at the level of the LIII vertebra. Results and conclusion. Comparing these indicators, it was found that using specific cut-off points, only the SMI proved to be statistically more reliable than the PMI, and therefore SMI is preferable for use in the diagnosis of sarcopenia. Since there are no standardized cut-off points for sarcopenia, it is impossible to definitely declare the failure of the PMI indicator directly. This result does not prove the impossibility of using the PMI criterion. The received indicators point the expediency of further studying the phenomenon of sarcopenia in cancer patients with a large sample. Nowadays, there is no wide-accepted method for radiological diagnosis of sarcopenia. Diagnosis of sarcopenia using CT is undoubtedly the most important step in reducing complications and improving the quality of treatment for both cancer and other diseases patients. Further search for CT indicators and their cut-off points is necessary for a more convenient and accurate diagnosis of sarcopenia.