İstanbul Sağlık ve Teknoloji Üniversitesi Kurumsal Akademik Arşivi
DSpace@İSTÜN, Üniversite mensupları tarafından doğrudan ve dolaylı olarak yayınlanan; kitap, makale, tez, bildiri, rapor, araştırma verisi gibi tüm akademik kaynakları uluslararası standartlarda dijital ortamda depolar, Üniversitenin akademik performansını izlemeye aracılık eder, kaynakları uzun süreli saklar ve telif haklarına uygun olarak Açık Erişime sunar.
Güncel Gönderiler
Braindetective: An advanced deep learning application for early detection, segmentation and classification of brain tumours using MRI images
(Springer Nature Link, 2025) Tokatlı, Nazlı; Bayram, Mücahit; Ogur, Hatice; Kılıç, Yusuf; Han, Vesile; Batur, Kutay Can; Altun, Halis
This study aims to create deep learning models for the early identification and classification of brain tumours. Models like U-Net, DAU-Net, DAU-Net 3D, and SGANet have been used to evaluate brain MRI images accurately. Magnetic resonance imaging (MRI) is the most commonly used method in brain tumour diag nosis, but it is a complicated procedure due to the brain’s complex structure. This study looked into the ability of deep learning architectures to increase the accuracy of brain tumour diagnosis. We used the BraTS 2020 dataset to segment and classify brain tumours. The U-Net model designed for the project achieved an accuracy rate of 97% with a loss of 47%, DAU-Net reached 90% accuracy with a loss of 33%, DAU-Net 3D achieved 99% accuracy with a loss of 35%, and SGANet achieved 99% accuracy with a loss of 20%, all demonstrating effective outcomes. These find ings aim to improve patient care quality by speeding up medical diagnosis processes using computer-aided technology. Doctors can detect 3D tumours from MRI pictures using software developed as part of the research. The work packages correctly han dled project management throughout the study’s data collection, model creation, and evaluation stages. Regarding brain tumour segmentation, 3D U-Net architecture with multi-head attention mechanisms provides doctors with the best tools for planning surgery and giving each patient the best treatment options. The user-friendly Turkish interface enables simple MRI picture uploads and quick, understandable findings.
Dental shade assessment via various digital photograph parameters: A pilot study
(EPA - TPID, 2025) Yılmaz, Seval Fatma; Ayvalıoğlu Şamiloğlu, Demet Çağıl
OBJECTIVES: Accurate shade matching is essential for successful restorative and prosthodontic dental treatments. Various methods, including visual, digital, and spectrophotometric techniques, have been utilized for shade selection. However, there is limited data regarding the optimal photographic parameters that yield the most accurate shade matching in digital photography. This pilot study aims to evaluate color differences arising from variations in photographic parameters -specifically camera aperture and ISO-while maintaining a constant shutter speed of 1/125. MATERIALS-METHODS: Spectrophotometric shade analysis (VITA Easyshade) was performed ten times on the maxillary right central incisor of a subject and the A1 tab from the VITA Classical shade guide before photography. A total of 12 digital images were captured using a DSLR camera (Canon EOS 850D) equipped with a 100 mm macro lens and ring flash (without polarized filter). The photographic parameters included a constant shutter speed (1/125 s), varying aperture values (f/11, f/13,f/22, f/32), and ISO values (100,160,200). Colorimetric evaluations were conducted using Adobe Photoshop, analyzing CIE Lab* coordinates and calculating ΔE values. RESULTS: The lowest ∆E value was recorded with ISO 200, f/32 aperture, and 1/125 shutter speed in the tooth group (5.41 ± 1.92), while the highest ∆E value was obtained with ISO 100, f/11 aperture, and 1/250 shutter speed in the shade guide group (62.14 ± 3.90). The digital photographic ∆E values mostly remained within the clinically unacceptable threshold (ΔE > 2.7 and ≤ 5.4). CONCLUSION: Within the limitations of this pilot study, digital photography alone for shade selection remains inconclusive.Further studies are warranted to comprehensively compare shade-matching accuracy using digital photography.
Artificial intelligence in planetary science and astronomy: Applications and research potential
(Euro Planet, 2025) Kacholia, Devanshi; Verma, Nimisha; D’Amore, Mario; Angrisani, Marianna; Frigeri, Alessandro; Schmidt, Frédéric; Carruba, Valerio; Hatipoğlu, Y. Güray; Roos-Serote, Maarten; Smirnov, Evgeny; Vergara Sassarini, Natalia Amanda; Solmaz, Arif; Oszkiewicz, Dagmara; Ivanovski, Stavro
Artificial Intelligence (AI) is one of the most influential fields of the 21st century (Zhang et al., 2021). Rich, E (2019) candidly described it as “the study of how to make computers do things which, at the moment, people do better”, today AI often surpasses human ability in tasks like large scale data mining and pattern recognition - its true strength. AI’s subfields - Machine Learning (ML) and deep learning (DL), play a critical role in expanding the usage to a vast variety of fields like planetary science, astronomy, earth observations, and remote sensing, just to name a few. There is an expected inclination towards incorporating AI more frequently in the studies of planetary science given the vast and complex nature of planetary data. In fact, AI has already been instrumental in extracting meaningful insights and advancing research in both interplanetary and astronomical studies. In planetary sciences, several AI techniques have been employed in order to bridge gaps in our understanding of the varied patterns and occurrences for studying the natural features observable from the data returned by scientific payloads. For example, PCA and cluster analysis can help in detecting patterns of compositional variation from multi and hyper-spectral imagery (Moussaoui et al., 2008; D’Amore & Padovan, 2022). Furthermore, to study specific features and patterns in their occurrences, correlations with neighbouring features; unsupervised algorithms and more complex -supervised techniques can be helpful depending on the scale of the task. From simple methods of unsupervised learning like clustering used to study the spectral signatures of Jezero crater on Mars (Pletl et al., 2023) to applying large language models to track asteroids affected by gravitational effects which alter the asteroid’s orbit (Carruba et al., 2025), such applications highlight the prospects of AI in the field of planetary science. Henceforth, to develop a deeper understanding of the potential and applications of ML, below is a typical AI workflow.
Planetary research: A new diamond open access journal for planetary science
(Euro Planet, 2025) Attree, Nicholas; Crameri, Fabio; Broquet, Adrien; Seignovert, Benoît; Hatipoğlu, Güray; Solmaz, Arif; Wieczorek, Mark
Planetary Research is a new diamond open-access journal for the planetary sciences and is set to be launched in January 2026. Planetary Research will follow an alternative to the traditional model of commercial publishing: the diamond open access model, whereby the journal is run entirely by volunteers using free and open-source software, and owned by the community, through a non-profit association that has been set up in France (The Planetary Research Cooperative). This means that all articles published in Planetary Research will be available for free for both authors and readers, with no access, subscription, or submission processing charges, whilst the journal scope and principles are determined by the community through participation in the online forum and monthly meetings. Further opportunities for participation include open calls for the positions of editor-in chief, editors, associate editors, and members of the media team and technical team, with deadlines on July the 1st, 2025 (see https://planetary-research.org for details).
Europlanet machine learning working group: A year of progress
(Euro Planet, 2025) Ivanovski, Stavro Lambrov; Verma, Nimisha; Hatipoğlu, Güray; Angrisani, Marianna; Solmaz, Arif; Smirnov, Evgeny; Carruba, Valerio; Kacholia, Devanshi; Oszkiewicz, Dagmara; D'Amore, Mario
The rapid advances in machine learning (ML) present unprecedented opportunities for planetary science. We have established a dedicated working group (WG) focused on the application of ML in this field to harness these technological advancements, address complex scientific questions, and enhance our understanding of planetary systems. The Europlanet Machine Learning Working Group held its kick-off meeting during the EPSC 2024 in Berlin, September 2024. The discussion focused on launching the group for exchanging ideas and opportunities with people within and outside of Europlanet’s membership for the first year of its launch. Some of the main goals established were to create a knowledge-sharing platform for members to share their research and invite collaboration, form sub-groups within the WG to expand on current research focus, and foster new collaborative research opportunities within or outside of Europlanet with new funding.
