29 research outputs found
Tackling the small data problem in medical image classification with artificial intelligence: a systematic review
No full textBackground: Though medical imaging has seen a growing interest in AI research, training models
require a large amount of data. In this domain, there are limited sets of data available as collecting
new data is either not feasible or requires burdensome resources. Researchers are facing with the
problem of small datasets and have to apply tricks to fight overfitting.
Methods: 147 peer-reviewed articles were retrieved from PubMed, published in English, up until 31
July 2022 and articles were assessed by two independent reviewers. We followed the PRISMA
guidelines for the paper selection and 77 studies were regarded as eligible for the scope of this review.
Adherence to reporting standards was assessed by using TRIPOD statement (transparent reporting of
a multivariable prediction model for individual prognosis or diagnosis).
Results: To solve the small data issue transfer learning technique, basic data augmentation and GAN
were applied in 75%, 69% and 14% of cases, respectively. More than 60% of the authors performed a
binary classification given the data scarcity and the difficulty of the tasks. Concerning
generalizability, only 4 studies explicitly stated an external validation of the developed model was
carried out. Full access to all datasets and code was severely limited (unavailable in more than 80% of
studies). Adherence to reporting standards was suboptimal (<50% adherence for 13 of 37 TRIPOD
items).
Conclusion: The goal of this review is to provide a comprehensive survey of recent advancements in
dealing with small medical images samples size. Transparency and improve quality in publications as
well as follow existing reporting standards are also supported
Recommended from our members
Lectura super usibus feudorum ;:Liber nonus.
No full textThis is a massive treatise on Medieval civil law. Ubaldo degli Ubaldi was a doctor of civil law in Perugia (Italy) his hometown. His "Liber feudorum" contained in this manuscript is followed by a brief account of the author's life, with an obituary note at the end. On fol. 182r begins another unidentified text about civil law: the author was possibly Jacopo Bottrigari, as the colophon says, but no other evidence was found
Lectura super usibus feudorum ;:Liber nonus.
No full textThis is a massive treatise on Medieval civil law. Ubaldo degli Ubaldi was a doctor of civil law in Perugia (Italy) his hometown. His "Liber feudorum" contained in this manuscript is followed by a brief account of the author's life, with an obituary note at the end. On fol. 182r begins another unidentified text about civil law: the author was possibly Jacopo Bottrigari, as the colophon says, but no other evidence was found
The Deterioration of Sarcopenia Post-Transarterial Radioembolization with Holmium-166 Serves as a Predictor for Disease Progression at 3 Months in Patients with Advanced Hepatocellular Carcinoma: A Pilot Study
No full textPurpose: The aim of this pilot study is to explore the relationship between changes in sarcopenia before and after one to three months of Transarterial Radioembolization (TARE) treatment with Holmium-166 (166Ho) and its effect on the rate of local response. Our primary objective is to assess whether the worsening of sarcopenia can function as an early indicator of a subgroup of patients at increased risk of disease progression in cases of hepatocellular carcinoma (HCC). Methods: A single-center retrospective analysis was performed on 25 patients with HCC who underwent 166Ho-TARE. Sarcopenia status was defined according to the measurement of the psoas muscle index (PMI) at baseline, one month, and three months after TARE. Radiological response according to mRECIST criteria was assessed and patients were grouped into responders and non-responders. The loco-regional response rate was evaluated for all patients before and after treatment, and was compared with sarcopenia status to identify any potential correlation. Results: A total of 20 patients were analyzed. According to the sarcopenia status at 1 month and 3 months, two groups were defined as follows: patients in which the deltaPMI was stable or increased (No-Sarcopenia group; n = 12) vs. patients in which the deltaPMI decreased (Sarcopenia group; n = 8). Three months after TARE, a significant difference in sarcopenia status was noted (p = 0.041) between the responders and non-responders, with the non-responder group showing a decrease in the sarcopenia values with a median deltaPMI of −0.57, compared to a median deltaPMI of 0.12 in the responder group. Therefore, deltaPMI measured three months post-TARE can be considered as a predictive biomarker for the local response rate (p = 0.028). Lastly, a minor deltaPMI variation (>−0.293) was found to be indicative of positive treatment outcomes (p = 0.0001). Conclusion: The decline in sarcopenia three months post-TARE with Holmium-166 is a reliable predictor of worse loco-regional response rate, as evaluated radiologically, in patients with HCC. Sarcopenia measurement has the potential to be a valuable assessment tool in the management of HCC patients undergoing TARE. However, further prospective and randomized studies involving larger cohorts are necessary to confirm and validate these findings
Congenital Tremor in Piglets: Clinico-Pathological Features and Aetiological Investgations
No full textAdverse Events to Comirnaty Vaccine Are Linked to Sex, Age and BMI: Should We Consider Reducing the Dose for Females?
No full textAn important issue that is often neglected is the difference between male and female genders in response to medical treatments. In the context of COVID-19 vaccine administration, despite identical protocol strategies, it has been observed that females often suffer more adverse consequences than males. Here, we analyzed the adverse events (AEs) of the Comirnaty vaccine in a population of 2385 healthcare workers as a function of age, sex, COVID-19 history and BMI. Using logistic regression analysis, we showed that these variables may contribute to the development of AEs, particularly in young subjects, females and individuals with a BMI below 25 kg/m2. Moreover, partial dependence plots indicate a 50% probability of developing a mild AE for a long period of time (≥7 days) or a severe AE of any duration in women below 40 years old and with a BMI < 20 kg/m2. As this effect is more evident after the second dose of the vaccine, we propose to reduce the amount of vaccine for any additional booster dose in relation to age, sex and BMI. This strategy might reduce adverse events without affecting vaccine efficacy
Sistemi di illuminazione pubblica: implementazione della comunicazione punto a punto su onde convogliate a banda stretta
No full textRadiomics and Machine Learning in Medical Image Analysis
No full textRadiomics is an emerging field of research in the context of medical image analysis. It is based on the extraction and analysis of quantitative imaging features from medical images in order to exploit them for clinical decision support.
In daily clinical practice, medical images are typically only visually assessed by radiologists. In this way a lot of potential meaningful information, which is not appreciable by the human eye, is lost.
Radiomics aims to use this information to help clinicians in different tasks, such as making diagnosis, predicting prognosis and therapeutic response of patients.
Descriptive quantities extracted from images are defined as radiomic features.
Very recently, an additional type of radiomic approach, called dosiomic, has been introduced. Dosiomic features are extracted from the dose distribution delivered in a radiotherapy treatment.
Machine learning (ML) and deep learning (DL) algorithms are successfully applied in many different fields, due to their capability to make predictions without being explicitly programmed.
Generally, ML and DL techniques are widely employed in radiomics to build predictive models.
In this thesis we discuss the analysis workflow that goes from the radiomic features extraction to the development of predictive models. In particular,
we explore the applicability and robustness of ML methods when working with small datasets.
In fact, in the field of medical imaging, it is often not easy to collect large annotated datasets.
From the operative point of view, in this work, we considered the following three different clinical problems, in which we tried to address clinical questions using radiomics: the investigation of the predictive role of dosiomic and radiomic features for radiotherapy treatment outcome; the evaluation of the predictive power of radiomic features extracted from CT in tumor staging and histology prediction; the evaluation of the predictive power of radiomic features extracted from multiparametric MRI in tumor grade prediction;
Concerning the first task, we implemented the feature extraction step from dose distributions available in a dataset collected by pediatric Hospital Meyer and Radiotherapy Unit of University of Florence within the Artificial Intelligence in Medicine (AIM) INFN project. The dataset is composed by patients affected by medulloblastoma and treated with radiotherapy. Currently, the dataset consists of 55 subjects.
Regarding the second question, we build predictive models to classify histology and tumor staging using features extracted from thoracic CT of Non Small Cell Lung Cancer (NSCLC) patients.
For this task, a subset of 130 subjects from the public dataset Lung1 Maastro NSCLC, and a private dataset of 47 subjects collected in a collaboration between A.R.N.A.S. Ospedale Civico Di Cristina Benfratelli, Università degli Studi di Palermo and INFN Catania are considered. %The
To address the last question, we consider a publicly available dataset of 167 patients from The Cancer Imaging Archive (TCIA) affected by glioma, which is a central nervous system tumor. Starting from features extracted from
multi-parametric MRI within tumor heterogeneous sub-regions, we build predictive models aimed at distinguishing the two grades of glioma labeled as low grade glioma and high grade glioma.
Feature extraction, feature analysis and machine learning models have been developed and implemented in Python language.
In our workflow, dimensionality reduction algorithms, such as principal component analysis (PCA), linear discriminant analysis (LDA) and mutual information (MI), are introduced to prevent overfitting.
The classifiers considered are: Support Vector Machines (SVM), Random Forest, Adaboost, and Nearest Neighbors.
The hyper-parameter optimization of the algorithms is performed through an exhaustive search. Actually, the optimization process turned out to be unstable. Therefore, we proceed with the assessment of performances using a nested cross-validation.
The metric chosen to report results are the balanced accuracy and the area under receiver operating characteristic curve (AUC).
The best performances obtained regarding stage classification of NSCLC
are reached by nearest neighbors classifier: AUC=0.80+/-0.05 and balanced accuracy=0.70+/-0.16.
In histology classification of NSCLC the results obtained considering the Random Forest classifier is: AUC=0.60+/-0.07.
Despite the issues due to small datasets, in some cases we achieve encouraging results. In particular, in glioma grade classification, we obtained for the Random Forest classifier, AUC=0.94+/-0.03 and a balanced accuracy=0.82+/-0.03.
In those cases in which the classifiers achieved satisfactory performances, we developed a ranking system to highlight the most important features in the classification problem.
This point, which concerns the explainability of machine learning algorithms, is crucial for possible future translation of radiomic approaches into the clinical diagnostic pathway
Developing an ensemble machine learning study: Insights from a multi-center proof-of-concept study
No full text
