Semantic Segmentation Framework for Glomeruli Detection and Classification in Kidney Histological Sections

Electronics

Antonio Brunetti¹  Nicola Altini¹  GiacomoDonato Cascarano¹  Francescomaria Marino¹  Vitoantonio Bevilacqua¹  Francesco Pesce²  MariaTeresa Rocchetti²  Silvia Matino²  Umberto Venere²  Loreto Gesualdo²  Michele Rossini² 

[1] Department of Electrical and Information Engineering (DEI), Polytechnic University of Bari, 70126 Bari, Italy;Department of Emergency and Organ Transplantation (DETO), Nephrology Unit, University of Bari Aldo Moro, 70126 Bari, Italy;

关键词: semantic segmentation;    convolutional neural networks;    kidney biopsy;    kidney transplantation;    glomerulus detection;    glomerulosclerosis;   

DOI  :  10.3390/electronics9030503

来源: DOAJ

【 摘 要 】

The evaluation of kidney biopsies performed by expert pathologists is a crucial process for assessing if a kidney is eligible for transplantation. In this evaluation process, an important step consists of the quantification of global glomerulosclerosis, which is the ratio between sclerotic glomeruli and the overall number of glomeruli. Since there is a shortage of organs available for transplantation, a quick and accurate assessment of global glomerulosclerosis is essential for retaining the largest number of eligible kidneys. In the present paper, the authors introduce a Computer-Aided Diagnosis (CAD) system to assess global glomerulosclerosis. The proposed tool is based on Convolutional Neural Networks (CNNs). In particular, the authors considered approaches based on Semantic Segmentation networks, such as SegNet and DeepLab v3+. The dataset has been provided by the Department of Emergency and Organ Transplantations (DETO) of Bari University Hospital, and it is composed of 26 kidney biopsies coming from 19 donors. The dataset contains 2344 non-sclerotic glomeruli and 428 sclerotic glomeruli. The proposed model consents to achieve promising results in the task of automatically detecting and classifying glomeruli, thus easing the burden of pathologists. We get high performance both at pixel-level, achieving mean F-score higher than 0.81, and Weighted Intersection over Union (IoU) higher than 0.97 for both SegNet and Deeplab v3+ approaches, and at object detection level, achieving 0.924 as best F-score for non-sclerotic glomeruli and 0.730 as best F-score for sclerotic glomeruli.

【 授权许可】

Unknown