Kimmo Kaski

Dr. Kimmo Kaski

orcid

Research Focus & Metrics

Academic Career Length

32Years (1995-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 July 2019 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JSJaakko Sahlsten
Jaakko Sahlsten
JJJoel Jaskari
Joel Jaskari
JKJyri Kivinen
Jyri Kivinen
LTLauri Turunen
Lauri Turunen
EJEsa Jaanio
Esa Jaanio
Kimmo KaskiKimmo Kaski
Kimmo Kaski
Diabetes is a globally prevalent disease that can cause visible microvascular complications such as diabetic retinopathy and macular edema in the human eye retina, the images of which are today used for manual disease screening and diagnosis. This labor-intensive task could greatly benefit from automatic detection using deep learning technique. Here we present a deep learning system that identifies referable diabetic retinopathy comparably or better than presented in the previous studies, although we use only a small fraction of images (<1/4) in training but are aided with higher image resolutions. We also provide novel results for five different screening and clinical grading systems for diabetic retinopathy and macular edema classification, including state-of-the-art results for accurately classifying images according to clinical five-grade diabetic retinopathy and for the first time for the four-grade diabetic macular edema scales. These results suggest, that a deep learning system could increase the cost-effectiveness of screening and diagnosis, while attaining higher than recommended performance, and that the system could be applied in clinical examinations requiring finer grading.

3 April 2020 in Scientific Reports
Verified
Journal Article
Open access
PDF file
JJJoel Jaskari
Joel Jaskari
JSJaakko Sahlsten
Jaakko Sahlsten
JJJorma Järnstedt
Jorma Järnstedt
HMHelena Mehtonen
Helena Mehtonen
KKKalle Karhu
Kalle Karhu
Kimmo KaskiKimmo Kaski
Kimmo Kaski
Accurate localisation of mandibular canals in lower jaws is important in dental implantology, in which the implant position and dimensions are currently determined manually from 3D CT images by medical experts to avoid damaging the mandibular nerve inside the canal. Here we present a deep learning system for automatic localisation of the mandibular canals by applying a fully convolutional neural network segmentation on clinically diverse dataset of 637 cone beam CT volumes, with mandibular canals being coarsely annotated by radiologists, and using a dataset of 15 volumes with accurate voxel-level mandibular canal annotations for model evaluation. We show that our deep learning model, trained on the coarsely annotated volumes, localises mandibular canals of the voxel-level annotated set, highly accurately with the mean curve distance and average symmetric surface distance being 0.56 mm and 0.45 mm, respectively. These unparalleled accurate results highlight that deep learning integrated into dental implantology workflow could significantly reduce manual labour in mandibular canal annotations.

1 March 2012 in Journal of Statistical Mechanics: Theory and Experiment
Verified
Journal Article
Closed access
MKMikko Kivelä
Mikko Kivelä
RPRaj Kumar Pan
Raj Kumar Pan
Kimmo KaskiKimmo Kaski
Kimmo Kaski
JKJános Kertész
János Kertész
JSJari Saramäki
Jari Saramäki
MKMárton Karsai
Márton Karsai

2 February 2021 in Ethics and Information Technology
Verified
Journal Article
Open access
PDF file
Mirco NanniMirco Nanni
Mirco Nanni
GAGennady Andrienko
Gennady Andrienko
ABAlbert-László Barabási
Albert-László Barabási
CBChiara Boldrini
Chiara Boldrini
FBFrancesco Bonchi
Francesco Bonchi
AVAlessandro Vespignani
Alessandro Vespignani
The rapid dynamics of COVID-19 calls for quick and effective tracking of virus transmission chains and early detection of outbreaks, especially in the “phase 2” of the pandemic, when lockdown and other restriction measures are progressively withdrawn, in order to avoid or minimize contagion resurgence. For this purpose, contact-tracing apps are being proposed for large scale adoption by many countries. A centralized approach, where data sensed by the app are all sent to a nation-wide server, raises concerns about citizens’ privacy and needlessly strong digital surveillance, thus alerting us to the need to minimize personal data collection and avoiding location tracking. We advocate the conceptual advantage of a decentralized approach, where both contact and location data are collected exclusively in individual citizens’ “personal data stores”, to be shared separately and selectively (e.g., with a backend system, but possibly also with other citizens), voluntarily, only when the citizen has tested positive for COVID-19, and with a privacy preserving level of granularity. This approach better protects the personal sphere of citizens and affords multiple benefits: it allows for detailed information gathering for infected people in a privacy-preserving fashion; and, in turn this enables both contact tracing, and, the early detection of outbreak hotspots on more finely-granulated geographic scale. The decentralized approach is also scalable to large populations, in that only the data of positive patients need be handled at a central level. Our recommendation is two-fold. First to extend existing decentralized architectures with a light touch, in order to manage the collection of location data locally on the device, and allow the user to share spatio-temporal aggregates—if and when they want and for specific aims—with health authorities, for instance. Second, we favour a longer-term pursuit of realizing a Personal Data Store vision, giving users the opportunity to contribute to collective good in the measure they want, enhancing self-awareness, and cultivating collective efforts for rebuilding society.

9 June 2017 in JMIR Research Protocols
Verified
Journal Article
Open access
TATalayeh Aledavood
Talayeh Aledavood
AHAna Maria Triana Hoyos
Ana Maria Triana Hoyos
TATuomas Alakörkkö
Tuomas Alakörkkö
Kimmo KaskiKimmo Kaski
Kimmo Kaski
JSJari Saramäki
Jari Saramäki
RDRichard K Darst
Richard K Darst
Mental and behavioral disorders are the main cause of disability worldwide. However, their diagnosis is challenging due to a lack of reliable biomarkers; current detection is based on structured clinical interviews which can be biased by the patient's recall ability, affective state, changing in temporal frames, etc. While digital platforms have been introduced as a possible solution to this complex problem, there is little evidence on the extent of usability and usefulness of these platforms. Therefore, more studies where digital data is collected in larger scales are needed to collect scientific evidence on the capacities of these platforms. Most of the existing platforms for digital psychiatry studies are designed as monolithic systems for a certain type of study; publications from these studies focus on their results, rather than the design features of the data collection platform. Inevitably, more tools and platforms will emerge in the near future to fulfill the need for digital data collection for psychiatry. Currently little knowledge is available from existing digital platforms for future data collection platforms to build upon. The objective of this work was to identify the most important features for designing a digital platform for data collection for mental health studies, and to demonstrate a prototype platform that we built based on these design features. We worked closely in a multidisciplinary collaboration with psychiatrists, software developers, and data scientists and identified the key features which could guarantee short-term and long-term stability and usefulness of the platform from the designing stage to data collection and analysis of collected data. The key design features that we identified were flexibility of access control, flexibility of data sources, and first-order privacy protection. We also designed the prototype platform Non-Intrusive Individual Monitoring Architecture (Niima), where we implemented these key design features. We described why each of these features are important for digital data collection for psychiatry, gave examples of projects where Niima was used or is going to be used in the future, and demonstrated how incorporating these design principles opens new possibilities for studies. The new methods of digital psychiatry are still immature and need further research. The design features we suggested are a first step to design platforms which can adapt to the upcoming requirements of digital psychiatry.

18 July 2022 in IEEE Access
Verified
Journal Article
Open access
JJJoel Jaskari
Joel Jaskari
JSJaakko Sahlsten
Jaakko Sahlsten
TDTheodoros Damoulas
Theodoros Damoulas
JKJeremias Knoblauch
Jeremias Knoblauch
SSSimo Sarkka
Simo Sarkka
Kimmo KaskiKimmo Kaski
Kimmo Kaski
Automatic classification of diabetic retinopathy from retinal images has been increasingly studied using deep neural networks with impressive results. However, there is clinical need for estimating uncertainty in the classifications, a shortcoming of modern neural networks. Recently, approximate Bayesian neural networks (BNNs) have been proposed for this task, but previous studies have only considered the binary referable/non-referable diabetic retinopathy classification applied to benchmark datasets. We present novel results for 9 BNNs by systematically investigating a clinical dataset and 5-class classification scheme, together with benchmark datasets and binary classification scheme. Moreover, we derive a connection between entropy-based uncertainty measure and classifier risk, from which we develop a novel uncertainty measure. We observe that the previously proposed entropy-based uncertainty measure improves performance on the clinical dataset for the binary classification scheme, but not to such an extent as on the benchmark datasets. It improves performance in the clinical 5-class classification scheme for the benchmark datasets, but not for the clinical dataset. Our novel uncertainty measure generalizes to the clinical dataset and to one benchmark dataset. Our findings suggest that BNNs can be utilized for uncertainty estimation in classifying diabetic retinopathy on clinical data, though proper uncertainty measures are needed to optimize the desired performance measure. In addition, methods developed for benchmark datasets might not generalize to clinical datasets.