Search

In this study, we train and compare three types of machine learning algorithms for Survival Analysis: Random Survival Forest, DeepSurv and DeepHit, using the SEER database to model cutaneous malignant melanoma. Additionally, we employ SurvLIMEpy library, a Python package designed to provide explainability for survival machine learning models, to analyse feature importance. The results demonstrate that machine learning algorithms outperform the Cox Proportional Hazards Model. Our work underscores the importance of explainability methods for interpreting black-box models and provides insights into important features related to melanoma prognosis., This research was supported by the Spanish Research Agency (AEI) under projects PID2020-116294GB-I00 and PID2020-116907RB-I00 of the call MCIN/ AEI /10.13039/501100011033, the project 718/C/2019 with id 201923-31 funded by Fundació la Marato de TV3 and the grant 2020 FI SDUR 306 funded by AGAUR., Peer Reviewed, Postprint (author's final draft)

Advancements in dermatological artificial intelligence research require high-quality and comprehensive datasets that mirror real-world clinical scenarios. We introduce a collection of 18,946 dermoscopic images spanning from 2010 to 2016, collated at the Hospital Clínic in Barcelona, Spain. The BCN20000 dataset aims to address the problem of unconstrained classification of dermoscopic images of skin cancer, including lesions in hard-to-diagnose locations such as those found in nails and mucosa, large lesions which do not fit in the aperture of the dermoscopy device, and hypo-pigmented lesions. Our dataset covers eight key diagnostic categories in dermoscopy, providing a diverse range of lesions for artificial intelligence model training. Furthermore, a ninth out-of-distribution (OOD) class is also present on the test set, comprised of lesions which could not be distinctively classified as any of the others. By providing a comprehensive collection of varied images, BCN20000 helps bridge the gap between the training data for machine learning models and the day-to-day practice of medical practitioners. Additionally, we present a set of baseline classifiers based on state-of-the-art neural networks, which can be extended by other researchers for further experimentation., We acknowledge the support of the International Skin Imaging Collaboration (ISIC). This research was supported by the Spanish Research Agency (AEI) under project PID2020-116907RB-I00 of the call MCIN/ AEI /10.13039/501100011033 and the project 718/C/2019 with id 201923-30 and 201923-31, funded by Fundació la Marató de TV3, iTOBOs grant from the European Union’s Horizon 2020 research and innovation programme num 965221. Other funding sources include the Melanoma Research Alliance Young Investigator Award 614197. This research was funded in part through the NIH/NCI Cancer Center Support Grant P30 CA008748., Peer Reviewed, Postprint (published version)

© 2024 Elsevier. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0, In this paper we present SurvLIMEpy, an open-source Python package that implements the SurvLIME algorithm. This method allows to compute local feature importance for machine learning algorithms designed for modelling Survival Analysis data. The presented implementation uses a matrix-wise formulation, which allows to speed up the execution time. Additionally, SurvLIMEpy assists the user with visualisation tools to better understand the result of the algorithm. The package supports a wide variety of survival models, from the Cox Proportional Hazards Model to deep learning models such as DeepHit or DeepSurv. Two types of experiments are presented in this paper. First, by means of simulated data, we study the ability of the algorithm to capture the importance of the features. Second, we use three open source survival datasets together with a set of survival algorithms in order to demonstrate how SurvLIMEpy behaves when applied to different models., Peer Reviewed, Postprint (author's final draft)

2023/2024, 1r quadrimestre

Resolved, 2023/2024, 1r quadrimestre

Resolved, 2022/2023, 1r quadrimestre

In this study, we train and compare three types of machine learning algorithms for Survival Analysis: Random Survival Forest, DeepSurv and DeepHit, using the SEER database to model cutaneous malignant melanoma. Additionally, we employ SurvLIMEpy library, a Python package designed to provide explainability for survival machine learning models, to analyse feature importance. The results demonstrate that machine learning algorithms outperform the Cox Proportional Hazards Model. Our work underscores the importance of explainability methods for interpreting black-box models and provides insights into important features related to melanoma prognosis., Preprint

In this paper we present SurvLIMEpy, an open-source Python package that implements the SurvLIME algorithm. This method allows to compute local feature importance for machine learning algorithms designed for modelling Survival Analysis data. Our implementation takes advantage of the parallelisation paradigm as all computations are performed in a matrix-wise fashion which speeds up execution time. Additionally, SurvLIMEpy assists the user with visualization tools to better understand the result of the algorithm. The package supports a wide variety of survival models, from the Cox Proportional Hazards Model to deep learning models such as DeepHit or DeepSurv. Two types of experiments are presented in this paper. First, by means of simulated data, we study the ability of the algorithm to capture the importance of the features. Second, we use three open source survival datasets together with a set of survival algorithms in order to demonstrate how SurvLIMEpy behaves when applied to different models.

Sentinel lymph node status is a crucial prognosis factor for melanomas; nonetheless, the invasive surgery required to obtain it always puts the patient at risk. In this study, we develop a Deep Learning-based approach to predict lymph node metastasis from Whole Slide Images of primary tumours. Albeit very informative, these images come with complexities that hamper their use in machine learning applications, namely their large size and limited datasets. We propose a pre-training strategy based on self-supervised contrastive learning to extract better image feature representations and an attention-based Multiple Instance Learning approach to enhance the model’s performance. With this work, we quantitatively demonstrate that combining both methods improves various classification metrics and qualitatively show that contrastive learning encourages the network to output higher attention scores to tumour tissue and lower scores to image artifacts., Work supported by the Spanish Research Agency (AEI) under project PID2020-116907RB-I00 of the call MCIN/AEI/10.13039/501100011033 and the project 718/C/ 2019 funded by Fundació la Marato de TV3., Peer Reviewed, Postprint (author's final draft)

Skin lesions are a severe disease globally. Early detection of melanoma in dermatoscopy im-ages significantly increases the survival rate. However, the accurate recognition of melanomais extremely challenging due to the following reasons: low contrast between lesions and skin,appearances of artifacts, etc. Hence, reliable automatic detection of skin tumors is very usefulto increase the accuracy and efficiency of dermatologists. In this MSc thesis we explore the useof contextual information to improve the performance of Deep Learning classifiers in the areaof skin lesion image classification. This information was obtained by means of patient embed-dings, attention, and a hand-crafted contextual sampler. The proposed methods were evaluatedon the ISIC 2020 dataset. Experimental results show that this techniques yield better results butthey are still not significant enough. It is necessary to make future research on other ways toaggregate this information.

INTRODUCCIÓN: En España, un tercio de los estudiantes universitarios presentan sobrepeso u obesidad. Una alimentación saludable, basada en la dieta mediterránea, junto con ejercicio físico regular, mejora parámetros de composición corporal y condición física. OBJETIVO: Estudiar la relación entre adherencia a la dieta mediterránea y variables específicas de composición corporal y condición física en estudiantes universitarios de Nutrición Humana y Dietética (NHyD). METODOLOGÍA: Estudio piloto en el que participaron 20 estudiantes del grado de NHyD. Se estudiaron variables de alimentación, utilizando el PREDIMED; de composición corporal, mediante una antropometría; y de condición física a través de diferentes pruebas. Se realizaron estadísticos descriptivos y correlaciones. RESULTADOS: Los resultados del PREDIMED fueron muy homogéneos, presentando todos una adherencia óptima (10,24±1,01). En relación a la composición corporal, la muestra presentaba Normopeso (23,54 ±2,78) y un porcentaje de grasa corporal de 10,9±2,66 en hombres y 12,83±1,47 en mujeres. Sólo se estableció una correlación significativa entre la adherencia a la dieta mediterránea y el test Side Bridge (R=0,049,p=0,710) en hombres. CONCLUSIÓN: No se observaron relaciones entre los hábitos alimentarios y las variables de composición corporal y condición física a excepción de una prueba de fuerza en el caso de los varones participantes en el estudio.

INTRODUCCIÓN: En España, un tercio de los estudiantes universitarios presentan sobrepeso u obesidad. Una alimentación saludable, basada en la dieta mediterránea, junto con ejercicio físico regular, mejora parámetros de composición corporal y condición física. OBJETIVO: Estudiar la relación entre adherencia a la dieta mediterránea y variables específicas de composición corporal y condición física en estudiantes universitarios de Nutrición Humana y Dietética (NHyD). METODOLOGÍA: Estudio piloto en el que participaron 20 estudiantes del grado de NHyD. Se estudiaron variables de alimentación, utilizando el PREDIMED; de composición corporal, mediante una antropometría; y de condición física a través de diferentes pruebas. Se realizaron estadísticos descriptivos y correlaciones. RESULTADOS: Los resultados del PREDIMED fueron muy homogéneos, presentando todos una adherencia óptima (10,24±1,01). En relación a la composición corporal, la muestra presentaba Normopeso (23,54 ±2,78) y un porcentaje de grasa corporal de 10,9±2,66 en hombres y 12,83±1,47 en mujeres. Sólo se estableció una correlación significativa entre la adherencia a la dieta mediterránea y el test Side Bridge (R=0,049,p=0,710) en hombres. CONCLUSIÓN: No se observaron relaciones entre los hábitos alimentarios y las variables de composición corporal y condición física a excepción de una prueba de fuerza en el caso de los varones participantes en el estudio.