Artificial intelligence assists identification and pathologic classification of glomerular lesions in patients with diabetic nephropathy.

BACKGROUND: Glomerular lesions are the main injuries of diabetic nephropathy (DN) and are used as a crucial index for pathologic classification. Manual quantification of these morphologic features currently used is semi-quantitative and time-consuming. Automatically quantifying glomerular morphologic features is urgently needed. METHODS: A series of convolutional neural networks (CNN) were designed to identify and classify glomerular morphologic features in DN patients. Associations of these digital features with pathologic classification and prognosis were further analyzed. RESULTS: Our CNN-based model achieved a 0.928 F1-score for global glomerulosclerosis and 0.953 F1-score for Kimmelstiel-Wilson lesion, further obtained a dice of 0.870 for the mesangial area and F1-score beyond 0.839 for three glomerular intrinsic cells. As the pathologic classes increased, mesangial cell numbers and mesangial area increased, and podocyte numbers decreased (p for all < 0.001), while endothelial cell numbers remained stable (p = 0.431). Glomeruli with Kimmelstiel-Wilson lesion showed more severe podocyte deletion compared to those without (p < 0.001). Furthermore, CNN-based classifications showed moderate agreement with pathologists-based classification, the kappa value between the CNN model 3 and pathologists reached 0.624 (ranging from 0.529 to 0.688, p < 0.001). Notably, CNN-based classifications obtained equivalent performance to pathologists-based classifications on predicting baseline and long-term renal function. CONCLUSION: Our CNN-based model is promising in assisting the identification and pathologic classification of glomerular lesions in DN patients.

Clinicopathological Characteristics of Light and Heavy Chain Deposition Disease: A Case Series.

RATIONALE & OBJECTIVE: Light and heavy chain deposition disease (LHCDD) is a rare form of monoclonal immunoglobulin (Ig) deposition disease, and limited clinical data are available characterizing this condition. Here we describe the clinicopathological characteristics and outcomes of LHCDD. STUDY DESIGN: Case series. SETTING & PARTICIPANTS: 13 patients with biopsy-proven LHCDD diagnosed between January 2008 and December 2022 at one of 2 Chinese medical centers. FINDINGS: Among the 13 patients described, 6 were men and 7 were women, with a mean age of 52.6±8.0 years. Patients presented with hypertension (76.9%), anemia (84.6%), increased serum creatinine concentrations (84.6%; median, 1.7mg/dL), proteinuria (100%; average urine protein, 3.0g/24h), nephrotic syndrome (30.8%), and microscopic hematuria (76.9%). Serum immunofixation electrophoresis showed monoclonal Ig for 11 patients (84.6%). Serum free light chain ratios were abnormal in 11 patients (84.6%), and heavy/light chain ratios were abnormal in 9 of 10 patients (90%) with available data. Five patients were diagnosed with multiple myeloma. A histological diagnosis of nodular mesangial sclerosis was made in 10 patients (76.9%). Immunofluorescence demonstrated deposits of IgG subclass in 7 patients (γ-κ, n=4; γ-λ, n=3) and IgA in 5 patients (α-κ, n=2; α-λ, n=3). Six patients underwent IgG subclass staining (γ1, n=3; γ2, n=2; γ3, n=1). The deposits of IgD-κ were confirmed by mass spectrometry in 1 patient. Among 12 patients for whom data were available during a median of 26.5 months, 11 received chemotherapy and 1 received conservative treatment. One patient died, and disease progressed to kidney failure in 3 (25%). Among the 9 patients evaluable for hematological and kidney disease progression, 5 (56%) had a hematologic response and 1 (11%) exhibited improvement in kidney disease. LIMITATIONS: Retrospective descriptive study, limited number of patients, urine protein electrophoresis or immunofixation electrophoresis test results missing for most patients. CONCLUSIONS: In this case series of LHCDD, light and heavy chain deposition in kidney tissues were most frequent with monoclonal IgG1-κ. Among patients with evaluable data, more than half had a hematologic response, but a kidney response was uncommon.

Advancing the application of the analytical renal pathology system in allograft IgA nephropathy patients.

BACKGROUND: The analytical renal pathology system (ARPS) based on convolutional neural networks has been used successfully in native IgA nephropathy (IgAN) patients. Considering the similarity of pathologic features, we aim to evaluate the performance of the ARPS in allograft IgAN patients and broaden its implementation. METHODS: Biopsy-proven allograft IgAN patients from two different centers were enrolled for internal and external validation. We implemented the ARPS to identify glomerular lesions and intrinsic glomerular cells, and then evaluated its performance. Consistency between the ARPS and pathologists was assessed using intraclass correlation coefficients. The association of digital pathological features with clinical and pathological data was measured. Kaplan-Meier survival curve and cox proportional hazards model were applied to investigate prognosis prediction. RESULTS: A total of 56 biopsy-proven allograft IgAN patients from the internal center and 17 biopsy-proven allograft IgAN patients from the external center were enrolled in this study. The ARPS was successfully applied to identify the glomerular lesions (F1-score, 0.696-0.959) and quantify intrinsic glomerular cells (F1-score, 0.888-0.968) in allograft IgAN patients rapidly and precisely. Furthermore, the mesangial hypercellularity score was positively correlated with all mesangial metrics provided by ARPS [Spearman's correlation coefficient (r), 0.439-0.472, and all p values < 0.001]. Besides, a higher allograft survival was noticed among patients in the high-level groups of the maximum and ratio of endothelial cells, as well as the maximum and density of podocytes. CONCLUSION: We propose that the ARPS could be implemented in future clinical practice with outstanding capability.

Adaptive dispersion compensation using a photonic integrated circuit finite impulse response filter.

Optical equalization can be used for chromatic dispersion compensation in optical communication systems to improve the system performance; however, optical signal processing (OSP) is generally specifically designed for transmission channels, that is non-adaptive to dynamic transmission distortions compared with digital signal processing (DSP). In this contribution, we demonstrate optical equalization using a photonic integrated circuit (PIC) filter for chromatic dispersion compensation, with static and adaptive techniques: (a) the static optical equalizer is calibrated based on the known fiber dispersion and length, by using the fractional delay reference method; (b) the adaptive optical equalizer is updated iteratively to compensate transmission impairments based on a least-mean squares (LMS) algorithm. Experimental results show that both the static optical equalizer and the adaptive optical LMS equalizer can give an 18-dB Q-factor for a 14-Gbd QPSK signal transmitting over 30 km. To highlight the capability of the optical equalizers, we use simulations to show the improvement in dispersion compensating characteristics by implementing additional taps.

The Spectrum of Biopsy-Proven Kidney Diseases, Causes, and Renal Outcomes in Acute Kidney Injury Patients.

INTRODUCTION: Acute kidney injury (AKI) is a group of highly heterogeneous, complicated clinical syndromes. Although kidney biopsy plays an irreplaceable role in evaluating complex AKI, a few studies have focused on the clinicopathology of AKI biopsies. This study analyzed the pathological disease spectrum, causes, and renal outcomes of biopsied AKI patients. METHODS: We retrospectively included 2,027 AKI patients who underwent kidney biopsies at a national clinical research center of kidney diseases from 2013 through 2018. To compare the biopsied AKI cases without and with coexisting glomerulopathy, patients were classified into acute tubular/tubulointerstitial nephropathy-associated AKI (ATIN-AKI) and glomerular disease-associated AKI (GD-AKI) groups. RESULTS: Of 2,027 biopsied AKI patients, 65.1% were male, with a median age of 43 years. A total of 1,590 (78.4%) patients had coexisting GD, while only 437 (21.6%) patients had ATIN alone. The AKI patients with GD mainly (53.5%) manifested as stage 1 AKI, while most ATIN-AKI patients (74.8%) had stage 3 AKI. In the ATIN-AKI group, 256 (58.6%) patients had acute interstitial nephritis (AIN), and 77 (17.6%) had acute tubular injury (ATI). ATIN-AKI was mainly caused by drugs in 85.5% of AIN and 63.6% of ATI cases, respectively. In AKI patients with coexisting GD, the leading pathological diagnoses in over 80% of patients were IgA nephropathy (IgAN, 22.5%), minimal change disease (MCD, 17.5%), focal segmental glomerulosclerosis (FSGS, 15.3%), lupus nephritis (LN, 11.9%), membranous nephropathy (MN, 10.2%), and ANCA-associated vasculitis (AAV, 4.7%). A total of 775 patients were followed up within 3 months after renal biopsy; ATIN-AKI patients achieved statistically higher complete renal recovery than the GD-AKI patients (83.5% vs. 70.5%, p < 0.001). CONCLUSIONS: Most biopsied AKI patients have coexisting GD, while ATIN alone is seen less frequently. ATIN-AKI is mainly caused by drugs. In GD-AKI patients, IgAN, MCD, FSGS, LN, MN, and AAV are the leading diagnoses. Compared to AKI patients without GD, patients with GD suffer from worse renal function recovery.