MSMikko Saukkoriipi

Mikko Saukkoriipi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mikko Saukkoriipi has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Virtual Reality for 3D AI Segmentation Verification in Clinical Radiology: a Human-Centered Approach

    by Lotta Orsmaa, Mikko Saukkoriipi, Jorma Järnstedt, Nastaran Rasouli, Kimmo Ronkainen, Jari Kangas, Kimmo Kaski, Roope Raisamo

  • Open Access

    Automating clinical information retrieval from Finnish electronic health records using large language models

    by Mikko Saukkoriipi, Nicole Hernandez, Jaakko Sahlsten, Kimmo Kaski, Otso Arponen

    Clinicians often need to search for patient-specific information within electronic health records (EHRs) containing years of heterogeneous longitudinal documentation, a task that can be time-consuming, cognitively demanding, and prone to oversight. We evaluated 14 locally deployable open-source large language models for structured patient-specific clinical information retrieval using a dataset comprising 1664 expert-annotated question–answer pairs from EHR-derived records of 183 Finnish patients undergoing breast cancer screening, diagnosis, or treatment under fully offline conditions. The records contained predominantly Finnish clinical text with occasional English and Latin terminology. The best-performing model, Llama-3.1-70B, achieved 95.3% accuracy and 97.3% consistency across semantically equivalent question formulations, while Qwen3-30B-A3B-2507 achieved comparable performance with lower measured memory use and latency under the standardized Transformers configuration. For the strongest models, accuracy was similar with and without predefined answer options in the prompt. Calibration varied across architectures, and 4-bit quantization reduced memory requirements while largely preserving accuracy. Medical-domain or Finnish-specialized models showed no systematic advantage over generalist models. Clinical review identified clinically significant errors in 2.9% of outputs, and semantically equivalent question formulations occasionally produced divergent clinical safety outcomes. These findings indicate that locally hosted open-source LLMs may support structured clinical information retrieval from longitudinal EHR-derived records, but clinically significant errors and sensitivity to question formulation remain limiting factors. Source attribution, prospective workflow validation, and human oversight are needed before clinical deployment.

  • Open Access

    Interactive Confidence Thresholding in Virtual Reality for AI-Assisted 3D MRI Segmentation of Mandibular Glands

    by Nastaran Rasouli, Lotta Orsmaa, Mikko Saukkoriipi, Jari Kangas, Jorma Järnstedt, Jaakko Sahlsten, Kimmo Kaski, Roope Raisamo

    Standard Three-dimensional (3D) Magnetic Resonance Imaging (MRI) segmentation models typically rely on a fixed threshold or argmax-based class selection, providing little or no insight into model uncertainty, which can limit clinician trust. In this work, we developed a framework that integrates a calibrated 3D U-Net into a Virtual Reality (VR) system, enabling clinicians to manipulate confidence thresholds in real time and observe how the segmentation changes. The network was trained to segment mandibular structures (submandibular glands and mandibular canal) on 55 T2-weighted MRI scans from the AAPM RT-MAC 2019 dataset and post hoc calibrated using temperature scaling. The VR application, built in Unity with OpenXR, offers two interaction modes: a single upper-threshold mode and a range mode that controls both lower and upper bounds. A user study with six clinicians was conducted to evaluate both modes using the UMUX-Lite questionnaire (from which a System Usability Scale (SUS)-equivalent score was derived), interaction logs, and qualitative feedback. Both modes were rated as highly usable, and narrower confidence intervals, focusing on the most reliable predictions, were more popular among users. The results suggest that enabling real-time adjustment of confidence thresholds improves the clarity of segmentation outputs and may support clinicians’ perceived confidence, as indicated by participants’ qualitative feedback and stated preferences.

  • Open Access

    Interactive AI annotation of medical images in a virtual reality environment

    by Lotta Orsmaa, Mikko Saukkoriipi, Jari Kangas, Nastaran Rasouli, Jorma Järnstedt, Helena Mehtonen, Jaakko Sahlsten, Joel Jaskari, Kimmo Kaski, Roope Raisamo

    Purpose:: Artificial intelligence (AI) achieves high-quality annotations of radiological images, yet often lacks the robustness required in clinical practice. Interactive annotation starts with an AI-generated delineation, allowing radiologists to refine it with feedback, potentially improving precision and reliability. These techniques have been explored in two-dimensional desktop environments, but are not validated by radiologists or integrated with immersive visualization technologies. We used a Virtual Reality (VR) system to determine whether (1) the annotation quality improves when radiologists can edit the AI annotation and (2) whether the extra work done by editing is worthwhile. Methods:: We evaluated the clinical feasibility of an interactive VR approach to annotate mandibular and mental foramina on segmented 3D mandibular models. Three experienced dentomaxillofacial radiologists reviewed AI-generated annotations and, when needed, refined them at the voxel level in 3D space through click-based interactions until clinical standards were met. Results:: Our results indicate that integrating expert feedback within an immersive VR environment enhances annotation accuracy, improves clinical usability, and offers valuable insights for developing medical image analysis systems incorporating radiologist input. Conclusion:: This study is the first to compare the quality of original and interactive AI annotation and to use radiologists’ opinions as the measure. More research is needed for generalization.