A multi-task convolutional neural network for classification and segmentation of chronic venous disorders

Abstract

Chronic Venous Disorders (CVD) of the lower limbs are one of the most prevalent medical conditions, affecting 35% of adults in Europe and North America. Due to the exponential growth of the aging population and the worsening of CVD with age, it is expected that the healthcare costs and the resources needed for the treatment of CVD will increase in the coming years. The early diagnosis of CVD is fundamental in treatment planning, while the monitoring of its treatment is fundamental to assess a patient’s condition and quantify the evolution of CVD. However, correct diagnosis relies on a qualitative approach through visual recognition of the various venous disorders, being time-consuming and highly dependent on the physician’s expertise. In this paper, we propose a novel automatic strategy for the joint segmentation and classification of CVDs. The strategy relies on a multi-task deep learning network, denominated VENet, that simultaneously solves segmentation and classification tasks, exploiting the information of both tasks to increase learning efficiency, ultimately improving their performance. The proposed method was compared against state-of-the-art strategies in a dataset of 1376 CVD images. Experiments showed that the VENet achieved a classification performance of 96.4%, 96.4%, and 97.2% for accuracy, precision, and recall, respectively, and a segmentation performance of 75.4%, 76.7.0%, 76.7% for the Dice coefficient, precision, and recall, respectively. The joint formulation increased the robustness of both tasks when compared to the conventional classification or segmentation strategies, proving its added value, mainly for the segmentation of small lesions.

Design optimization of medical robotic systems based on task performance metrics: A feasibility study for robotic guided vascular laser treatments

“…During the treatment, the physician must shoot the laser into the lesions, while the patient lies in a surgical bed. The treatment requires maintaining the laser beam perpendicular to the skin and on the center of the lesion, while keeping the distance to the target, avoiding overlaps between subsequent pulse shots (Adamič et al, 2015; Meesters et al, 2014; Oliveira et al, 2023) (Figure 2). To recreate these trajectories and cover all the possible lesion positions on the patient leg, the k th leg point, $${{\bf{p}}}_{{n}_{k}}\subset {{\bf{v}}}_{n^{\prime} }$$, from each human model are described in the space by its position and orientation concerning a world reference frame R‐xyz (i.e., world frame in Figure 4).…”

“…Meesters et al, 2014;Oliveira et al, 2023) (Figure 2). To recreate these trajectories and cover all the possible lesion positions on the patient leg, the k th leg point, p v n n ′ k ⊂ , from each human model are described in the space by its position and orientation concerning a world reference frame R-xyz (i.e., world frame in Figure 4).…”

An approach to the dermatological classification of histopathological skin images using a hybridized CNN-DenseNet model

“… Oliveira et al (2023) proposed a multitask CNN for classifying and segmenting chronic venous disorders. Their approach utilizes a single CNN architecture to address both classification and segmentation tasks.…”

“…Among the various pretrained models, DenseNet stands out as a densely connected convolutional network that encourages feature reuse and facilitates gradient flow throughout the network ( Kim, 2020 ; Oliveira et al, 2023 ). This architecture has demonstrated outstanding performance on benchmark image classification datasets, surpassing many other state-of-the-art models ( IEEE, 2020b ; Md.…”

CVINet: A deep learning based model for the diagnosis of chronic venous insufficiency in lower extremity using infrared thermal images

“…Oliveira et al 24 New Deep CNN model called as VENet Visible leg images from ULCER and SD-198 databases. • VENet has the potential to facilitate and expedite the diagnosis of chronic venous disease (CVD) lesions.…”