PART Ⅲ: Development And Evaluation Of Deep Learning Based Segmentation Of Histologic Structures in The Kidney Cortex With Multiple Histologic Stains

Contact: Audrey Hu (Whatsapp:008613880143964) Email: audrey.hu@wecistanche.com

Catherine P.Jayapandian, Yiiang Chen,Andrew R. Janowczyk & et al.

The assessment of renal biopsy is unique compared with other surgical pathology specimens because of the va-riety of stains routinely used.Morphologic assessment of histological preparations relies on the quality of the preparations itself, as well as the expertise of the pathologist in identifying normal and pathological structures. The authors demonstrate that "deep learning-based convolutional neural networks" may be employed for effcient and reliable segmentation of histologic structures across different stains of normal renal parenchyma using the Nephrotic Syndrome Study Network whole slide images. This dataset was curated from 38 histology laboratories and reflects substantial morphologic, technical,and stain heterogeneity. The findings provide useful insights, along with source code and data, which will help readers overcome challenges in this space. Taken together, this work represents a technical foundation from which future pathology tools may be built to enable actionable clinical decision sup-port tools for better disease characterization and risk assessment in pathology workflows.

CLICK HERE TO PART Ⅰ&Ⅱ

cistanche and cistanche extract

METHODS

Case and image dataset selection

This study was conducted using digital renal biopsies from the NEPTUNE digital pathology repository. NEPTUNE is a North American multicenter collaborative consortium with more than 650 adult and children enrolled from 29 recruiting sites(38 pathology laboratories).Only cases with a diagnosis of MCD were included in this study because histologically they are the most similar to normal renal parenchyma.A total of 459 curated WSIs(125 H&E,125 PAS, 102 SIL,107 TRI) from 125 MCD renal biopsies were used. Not all cases had all stains available in the digital pathology repository. Four WSIs were selected for each patient(1 WSI per stain). From each WSI,approximately 3 to 5 ROIs containing the histologic primitives were randomly selected, inspected by a pathologist, and manually extracted as 3000 ×3000 tiles then stored as 8-bit red reen blue (RGB)color images in PNG format at 40× digital magnification. Additional details on digitization and curation of biopsy WSIs can be found in Supplementary Figure S1.

Independent validation of the DL models. Six WSIs from 3 formalinfixed and paraffin embedded nephrectomy specimens were included to test the DL network performance for the segmentation of all histologic primitives on adult renal parenchyma without signif cant structural abnormalities. Sections from the nephrectomy specimens were stained with PAS, scanned into WSIs, and subsequently stained with a CD34 antibody, a marker of endothelial cells,and then rescanned into WSIs. One hundred seventy five random ROIs (3000×3000 pixels) were extracted from the PAS stained WSIs. The PAS-CD34 double stained WSIs were used as ground truth for validation of the DL segmentation approach for peritubular caillaies.

Histologic primitives and manual segmentation

Five renal pathologists manually segmented the ROIs to establish the ground truth for the histologic primitives (Table 2). Manual segmentations were generated using an open source software application.5 The ground truth annotations were saved as binary masks;that is, each pixel that was denoted as part of a histologic primitive (positive class pixels expressed as binary ls)or not (negative class pixels expressed as binary Os). Through this process, 30,048 annotations were made by pathologists on 1818 ROIs(Figure 10).

Six histologic primitives were used for this study:glomerular tuft, glomerular unit(tuft + Bowman's capsule), proximal tubular segments, distal tubular segments, arteries and arterioles, and peritubular capillaries. Consistent and detailed ground truth labels across all training samples can greatly facilitate robust DL performance, especially in segmentation tasks.24,32,3650-4 In order to produce consistent annotations across all images, each histologic primitive and its boundaries were carefully defined,and the annotation procedure for each use case standardized (Supplementary Figure S2). Furthermore, each annotation generated by a pathologist was reviewed by a second pathologist for quality assessment.

cistanche herb is a effective ingredient for kidney function improvement drugs

DL experimental pipeline and training methods

DL dataset. Up to four WSIs per biopsy(H&E, PAS, TRI,and SIL for each) were used for the segmentation of the glomerular tuft and unit, and proximal and distal tubular segments. Peritubular capillaries were segmented using only PAS WSIs, and arteries/arterioles were segmented only in H&E, PAS, and TRI WSIs (Table 2). WSIs were divided at the patient level into training, vali-dation, and testing sets(ratio 6:1:3).The networks were developed using WSIs of both adult and pediatric patients(Supplementary Figure S1). For training of the U-Net network,5 pathologists annotated 1196 glomerular tufts and units, 4669 proximal and 2285 distal tubular segments, 19,280 peritubular capillaries, and 2261 arteries/arterioles(Table 2).

Network configuration and training. Standard U-Net architecture with slightly tweaked parameters were implemented in PyTorch framework for training of each use case(Figure l1).Details of U-Net configuration, training methods including training set balancing and data augmentation can be found in Supplemental S3.

Detection and segmentation metrics. Detection and segmentation results were evaluated using F-Score, true positive rate/Values of (TPR), positive predictive value (PPV),and DSC. 0 and 1 represent the maximal discordance and agreement, respectively, between the pathologist ground truth and the U-Net results. TPR, PPV, and F-Score measure the detection accuracy of the DL networks. These metrics are computed using the number of correct segmentation results(true positives), incorrect segmentations(false positives), and missing segmentations(false negatives). DSC is the pixel wise spatial overlap index that measures the segmentation accuracy of the classifier, with values ranging from 0(indicating no spatial overlap between ground truth annotation and corresponding DL output mask) to 1(indicating complete overlap), and a DSC value >0.5 denoting a correct segmentation (true positive).

Number of training exemplars for different histologic primitives

To test how the number of manually annotated training exemplars influences network performance, we selected a representative set of histologic primitives based on size, complexity, distribution, and stain:glomerular tufts on H&E,peritubular capillaries on PAS, distal tubular segments on TRI,and arteries/arterioles on SIL. Specifically, we sought to evaluate the minimum number of annotated exemplars for standing up trained U-Net models for each type of histologic primitive. Toward this end, multiple U-Net models were trained for each type of primitive,each time with a greater number of annotated exemplars. Detection and segmentation accuracy were then computed for each such U-Net model for each primitive on the corresponding testing sets (Figure 8).

cistanche benefit: treat kindey diseases

Note: Cistanche is a well known traditioal medicinal herb for kidney diseases. cistanche contains main effective infgredients such as echinacoside and acteoside which can nourish kideny and improve kidney function. In 《SHENGNONG MEDICA》cistanche is recorded as the top herb for kindey function improvement purpose.