ImHistNet: Learnable Image Histogram Based DNN with Application to Noninvasive Determination of Carcinoma Grades in CT Scans
Lists
Only you see this
Abstract
Renal cell carcinoma (RCC) is the seventh most common cancer worldwide, accounting for an estimated 140,000 global deaths annually. Clear cell RCC (ccRCC) is the major subtype of RCC and its biological aggressiveness affects prognosis and treatment planning. An important ccRCC prognostic predictor is its ‘grade’ for which the 4-tiered Fuhrman grading system is used. Although the Fuhrman grade can be identified by percutaneous renal biopsy, recent studies suggested that such grades may be non-invasively identified by studying image texture features of the ccRCC from computed tomography (CT) data. Such image feature based identification currently mostly relies on laborious manual processes based on visual inspection of 2D image slices that are time-consuming and subjective. In this paper, we propose a learnable image histogram based deep neural network approach that can perform the Fuhrman low (I/II) and high (III/IV) grade classification for ccRCC in CT scans. Validated on a clinical CT dataset of 159 patients from the TCIA database, our method classified ccRCC low and high grades with 80% accuracy and 85% AUC.
BibTeX
@inproceedings{hussain2019imhistnet,
author = {Mohammad Arafat Hussain and Ghassan Hamarneh and Rafeef Garbi},
title = {{ImHistNet: Learnable Image Histogram Based DNN with Application to Noninvasive Determination of Carcinoma Grades in CT Scans}},
booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
year = {2019},
doi = {10.1007/978-3-030-32226-7\_15},
}Loading related content...