JNJanne Nurminen

Janne Nurminen

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Janne Nurminen has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Upper airway morphometry in acute neck infections: Clinical associations and deep learning–based segmentation

    by Ville Viertonen, Aapo Sirén, Aaro Widell, Jari-Pekka Vierula, Tatu Happonen, Mikko Nyman, Janne Nurminen, Heidi Huhtanen, Jussi Hirvonen

  • Open Access

    Segmentation-based morphometric analysis of neck abscesses on MRI: associations with disease severity

    by Ville Viertonen, Aapo Sirén, Jari-Pekka Vierula, Tatu Happonen, Mikko Nyman, Janne Nurminen, Jussi Hirvonen

    Objectives: Abscess diameter on MRI is an established predictor of clinical severity in neck infections, but this single measurement does not characterize three-dimensional morphology. This study evaluated whether segmentation-derived volume, sphericity, and compactness provide incremental prognostic value beyond conventional diameter. Materials and methods: In 227 consecutive patients with surgically confirmed neck abscesses, abscess masks were segmented on post-contrast T1-weighted MRI. Three morphometric features were extracted: volume, sphericity, and compactness; their associations with intensive care unit (ICU) admission and a prolonged hospital stay (exceeding 5 days) were evaluated using multivariable models. Results: Of 227 patients, 33 (15%) required ICU admission, and 40 (18%) had a prolonged hospital stay. Sphericity was lower in ICU patients (median 0.35 vs. 0.45, p = 6.6 × 10 − 5 ) and in those with prolonged stay ( p = 9.1 × 10 − 6 ). In multivariable models, volume improved upon manual diameter for ICU prediction (area under the curve 0.841 [95% CI 0.78–0.90] vs. 0.816 [0.74–0.88]); adding sphericity improved prolonged stay prediction (R 2 0.246 vs. 0.216, p = 0.005). Interobserver agreement was excellent (ICC 0.97–0.99). Conclusion: Segmentation-derived abscess volume, sphericity, and compactness provide complementary prognostic information beyond conventional diameter measurement for assessing neck infection severity. Key Points: Question Can segmentation-derived morphometric features of neck abscesses (volume, sphericity, compactness) improve prognostication of ICU admission and prolonged hospital stay beyond conventional diameter measurement on MRI? Findings Abscess volume outperformed manual diameter for predicting ICU admissions, and lower sphericity independently predicted prolonged hospital stay beyond abscess size in multivariable models . Clinical relevance Segmentation-derived morphometric features offer reproducible, quantitative tools for stratifying neck abscess severity in surgically managed patients; their value for guiding individual treatment decisions was not directly evaluated and warrants prospective validation .


  • Open Access

    Deep learning detects retropharyngeal edema on MRI in patients with acute neck infections

    by Oona Rainio, Heidi Huhtanen, Jari-Pekka Vierula, Janne Nurminen, Jaakko Heikkinen, Mikko Nyman, Riku Klén, Jussi Hirvonen

    Background: In acute neck infections, magnetic resonance imaging (MRI) shows retropharyngeal edema (RPE), which is a prognostic imaging biomarker for a severe course of illness. This study aimed to develop a deep learning-based algorithm for the automated detection of RPE. Methods: We developed a deep neural network consisting of two parts using axial T2-weighted water-only Dixon MRI images from 479 patients with acute neck infections annotated by radiologists at both slice and patient levels. First, a convolutional neural network (CNN) classified individual slices; second, an algorithm classified patients based on a stack of slices. Model performance was compared with the radiologists’ assessment as a reference standard. Accuracy, sensitivity, specificity, and area under receiver operating characteristic curve (AUROC) were calculated. The proposed CNN was compared with InceptionV3, and the patient-level classification algorithm was compared with traditional machine learning models. Results: Of the 479 patients, 244 (51%) were positive and 235 (49%) negative for RPE. Our model achieved accuracy, sensitivity, specificity, and AUROC of 94.6%, 83.3%, 96.2%, and 94.1% at the slice level, and 87.4%, 86.5%, 88.2%, and 94.8% at the patient level, respectively. The proposed CNN was faster than InceptionV3 but equally accurate. Our patient classification algorithm outperformed traditional machine learning models. Conclusion: A deep learning model, based on weakly annotated data and computationally manageable training, achieved high accuracy for automatically detecting RPE on MRI in patients with acute neck infections. Relevance statement: Our automated method for detecting relevant MRI findings was efficiently trained and might be easily deployed in practice to study clinical applicability. This approach might improve early detection of patients at high risk for a severe course of acute neck infections. Key Points: Deep learning automatically detected retropharyngeal edema on MRI in acute neck infections. Areas under the receiver operating characteristic curve were 94.1% at the slice level and 94.8% at the patient level. The proposed convolutional neural network was lightweight and required only weakly annotated data. Graphical


  • Open Access

    MRI-based risk factors for intensive care unit admissions in acute neck infections

    by Jari-Pekka Vierula, Harri Merisaari, Jaakko Heikkinen, Tatu Happonen, Aapo Sirén, Jarno Velhonoja, Heikki Irjala, Tero Soukka, Kimmo Mattila, Mikko Nyman, et al.


  • Open Access

    Pictorial Review of MRI Findings in Acute Neck Infections in Children

    by Janne Nurminen, Jaakko Heikkinen, Tatu Happonen, Mikko Nyman, Aapo Sirén, Jari-Pekka Vierula, Jarno Velhonoja, Heikki Irjala, Tero Soukka, Lauri Ivaska, et al.

    Pediatric neck infections and their complications, such as abscesses extending to deep neck compartments, are potentially life-threatening acute conditions. Medical imaging aims to verify abscesses and their extensions and exclude other complications. Magnetic resonance imaging (MRI) has proven to be a useful and highly accurate imaging method in acute neck infections in children. Children and adults differ in terms of the types of acute infections and the anatomy and function of the neck. This pictorial review summarizes typical findings in pediatric patients with neck infections and discusses some difficulties related to image interpretation.


  • MRI of odontogenic maxillofacial infections: diagnostic accuracy and reliability

    by Jaakko Heikkinen, Viljami Viljami, Janne Nurminen, Ville Jussila, Jarno Velhonoja, Heikki Irjala, Tero Soukka, Tatu Happonen, Jorma Järnstedt, Mikko Nyman, et al.

    Objectives To determine the diagnostic accuracy of emergency magnetic resonance imaging (MRI) in odontogenic maxillofacial infections, the clinic |

  • Open Access

    MRI of odontogenic maxillofacial infections: diagnostic accuracy and reliability

    by Jaakko Heikkinen, Viljami Jokihaka, Janne Nurminen, Ville Jussila, Jarno Velhonoja, Heikki Irjala, Tero Soukka, Tatu Happonen, Jorma Järnstedt, Mikko Nyman, et al.

    Objectives: To determine the diagnostic accuracy of emergency magnetic resonance imaging (MRI) in odontogenic maxillofacial infections, the clinical and surgical significance of MRI findings, and whether MRI can identify the tooth responsible for the infection. Methods: A retrospective cohort study reviewed 106 emergency neck MRI scans of patients with neck infections of odontogenic origin. The diagnostic accuracy of MRI in identifying abscesses was studied relative to surgical findings. Correlations were analyzed between various MRI findings and clinical results and outcomes, such as the surgical approach (intraoral vs. extraoral). The ability of MRI findings to predict the causative tooth was assessed in a blinded multi-reader setting. Results: Of the 106 patients with odontogenic infections, 77 (73%) had one or more abscesses. Imaging showed a sensitivity, specificity, and accuracy of 0.95, 0.84, and 0.92, respectively, for MRI diagnosis of an odontogenic abscess. Among the imaging findings, mediastinal edema was the strongest predictor of extraoral surgery. MRI showed bone marrow edema in the majority of patients, and multi-reader assessment showed good reliability. MRI was also able to predict the causative tooth accurately. Conclusions: Emergency neck MRI can accurately detect odontogenic abscesses and reliably point to the causative tooth. These results can increase the utility and reliance on emergency MRI in clinical decision-making.


  • Open Access

    Magnetic resonance imaging findings in pediatric neck infections—a comparison with adult patients

    by Janne Nurminen, Jaakko Heikkinen, Tatu Happonen, Jarno Velhonoja, Heikki Irjala, Tero Soukka, Lauri Ivaska, Kimmo Mattila, Jussi Hirvonen

    Background: Differences in the functioning of the immune system and the anatomical proportions of the neck between children and adults lead to different manifestations of deep neck infections. Magnetic resonance imaging (MRI) may serve as an alternative to computed tomography (CT) as the primary imaging modality. Objective: To study characteristic MRI findings and the diagnostic accuracy of MRI in pediatric deep neck infections. Materials and methods: We retrospectively studied a cohort of pediatric patients who underwent a neck 3-tesla MRI study over a five-year period. Inclusion criteria were: 1) emergency MRI findings indicating an infection, 2) infection as the final clinical diagnosis, 3) diagnostic image quality verified by the radiologist reading the study and 4) age under 18 years. Patient record data, including surgery reports, were compared with the MRI findings. Results: Data of 45 children were included and analysed. Compared to adults, children had a higher incidence of retropharyngeal infection and lymphadenitis, and a lower incidence of peritonsillar/parapharyngeal infection. MRI showed evidence of an abscess in 34 children. Of these 34 patients, 24 underwent surgery, which confirmed an abscess in 21 but no abscess in three patients. In addition, three patients underwent surgery without MRI evidence of abscess, and an abscess was found in one of these cases. The measures of diagnostic accuracy among the children were sensitivity 0.96, specificity 0.77, positive predictive value 0.89, negative predictive value 0.91 and accuracy 0.89. Compared with adults, children had lower C-reactive protein, but a similar proportion of them had an abscess, and abscess size and rate of surgery were similar. Conclusion: Despite the differences in the infection foci, emergency MRI in children had equal diagnostic accuracy to that in adults.


  • MRI Findings in Acute Tonsillar Infections

    by J. Heikkinen, J. Nurminen, J. Velhonoja, H. Irjala, T. Soukka, T. Happonen, M. Nyman, K. Mattila, J. Hirvonen

    BACKGROUND AND PURPOSE: Previous literature is vague on the prevalence and exact nature of abscesses in tonsillar infections, ranging from intratonsillar and peritonsillar collections to deep extension involving the parapharyngeal and retropharyngeal spaces. MR imaging has excellent diagnostic accuracy in detecting neck infections and can potentially clarify this issue. We sought to characterize the spectrum of MR imaging findings regarding tonsillar infections. MATERIALS AND METHODS: We conducted a retrospective cohort study of emergency neck MR imaging scans of patients with tonsillar infections. Imaging data were assessed in terms of signs of infection and the location of abscesses and were compared with clinical findings, final diagnoses, and surgical findings as reference standards. RESULTS: The study included 132 patients with tonsillar infection. Of these, 110 patients (83%) had ≥1 abscess (99 unilateral, 11 bilateral; average volume, 3.2 mL). Most abscesses were peritonsillar, and we found no evidence of intratonsillar abscess. Imaging showed evidence of parapharyngeal and retropharyngeal extension in 36% and 10% of patients, respectively. MR imaging had a high positive predictive value for both abscesses (0.98) and deep extension (0.86). Patients with large abscesses and widespread edema patterns had a more severe course of illness. CONCLUSIONS: Emergency neck MR imaging can accurately describe the extent and nature of abscess formation in tonsillar infections.