Performance of an Artificial Multi-observer Deep Neural Network for Fully Automated Segmentation of Polycystic Kidneys

Abstract

Deep learning techniques are being rapidly applied to medical imaging tasks—from organ and lesion segmentation to tissue and tumor classification. These techniques are becoming the leading algorithmic approaches to solve inherently difficult image processing tasks. Currently, the most critical requirement for successful implementation lies in the need for relatively large datasets that can be used for training the deep learning networks. Based on our initial studies of MR imaging examinations of the kidneys of patients affected by polycystic kidney disease (PKD), we have generated a unique database of imaging data and corresponding reference standard segmentations of polycystic kidneys. In the study of PKD, segmentation of the kidneys is needed in order to measure total kidney volume (TKV). Automated methods to segment the kidneys and measure TKV are needed to increase measurement throughput and alleviate the inherent variability of human-derived measurements. We hypothesize that deep learning techniques can be leveraged to perform fast, accurate, reproducible, and fully automated segmentation of polycystic kidneys. Here, we describe a fully automated approach for segmenting PKD kidneys within MR images that simulates a multi-observer approach in order to create an accurate and robust method for the task of segmentation and computation of TKV for PKD patients. A total of 2000 cases were used for training and validation, and 400 cases were used for testing. The multi-observer ensemble method had mean ± SD percent volume difference of 0.68 ± 2.2% compared with the reference standard segmentations. The complete framework performs fully automated segmentation at a level comparable with interobserver variability and could be considered as a replacement for the task of segmentation of PKD kidneys by a human.

A Practical Guide for Treatment of Rapidly Progressive ADPKD with Tolvaptan

“…Variants of these methods have been automated and validated and we expect that they will become increasingly accessible and available for disease prognostication. 29,30 Once a patient is determined to have typical ADPKD, the Mayo class should be ascertained (Figure 4). Patients in class 1A progress slowly and should not be treated.…”

Volumetric assessment of unaffected parenchyma and Wilms’ tumours: analysis of response to chemotherapy and surgery using a semi‐automated segmentation algorithm in children with renal neoplasms

“…Advances in computer science have created exciting new venues for complex data analyses. This includes automation, machine learning and artificial intelligence, which are rapidly being explored and integrated into medical research in nearly every field . The present study represents an early evaluation of this technology for paediatric patients with WT, which to our knowledge, has not been previously reported.…”

“…In addition, they stated that the auto technique did not require user experience or expertise for production of accurate results. Kline et al used auto‐segmentation for assessment of polycystic kidneys, and reported high accuracy. Applying fully automatic techniques for segmentation in WT seems to be an obvious next step to improve ease and efficiency of use.…”

Recent Advances in the Management of Autosomal Dominant Polycystic Kidney Disease

“…Stereology is faster than planimetry but does not segment the kidney, which is a requirement for advanced image analysis. Fast, automatic segmentations, including a deep learning-based, fully automated approach capable to replace humans for the task of segmenting polycystic kidneys, have been developed (5,6). Once segmented, advanced magnetic resonance image processing and analysis, such as texture analysis, may be superior and/ or complementary to TKV in predicting or measuring disease progression (7).…”