Multi-class tissue-type classification of colorectal cancer (CRC) histopathologic images is a significant step in the development of downstream machine learning models for diagnosis and treatment planning. However, publicly available CRC datasets used to build tissue classifiers often suffer from insufficient morphologic diversity, class imbalance, and low-quality image tiles, limiting downstream model performance and generalizability. To address this research gap, we introduce STARC-9 (STAnford coloRectal Cancer), a large-scale dataset for multi-class tissue classification. STARC-9 comprises 630,000 histopathologic image tiles uniformly sampled across nine clinically relevant tissue classes (each represented by 70,000 tiles), systematically extracted from hematoxylin & eosin-stained whole-slide images (WSI) from 200 CRC patients at the Stanford University School of Medicine. To construct STARC-9, we propose a novel framework, DeepCluster++, consisting of two primary steps to ensure diversity within each tissue class, followed by pathologist verification.

Deep learning has made significant strides in automated brain tumor segmentation from magnetic resonance imaging (MRI) scans in recent years. However, the reliability of these tools is hampered by the presence of poor-quality segmentation outliers, particularly in out-of-distribution samples, making their implementation in clinical practice difficult. Therefore, there is a need for quality control (QC) to screen the quality of the segmentation results. Although numerous automatic QC methods have been developed for segmentation quality screening, most were designed for cardiac MRI segmentation, which involves a single modality and a single tissue type. Furthermore, most prior works only provided subject-level predictions of segmentation quality and did not identify erroneous parts segmentation that may require refinement. To address these limitations, we proposed a novel multi-task deep learning architecture, termed QCResUNet, which produces subject-level segmentation-quality measures as well as voxel-level segmentation error maps for each available tissue class. To validate the effectiveness of the proposed method, we conducted experiments on assessing its performance on evaluating the quality of two distinct segmentation tasks. First, we aimed to assess the quality of brain tumor segmentation results. For this task, we performed experiments on one internal and two external datasets. Second, we aimed to evaluate the segmentation quality of cardiac Magnetic Resonance Imaging (MRI) data from the Automated Cardiac Diagnosis Challenge. The proposed method achieved high performance in predicting subject-level segmentation-quality metrics and accurately identifying segmentation errors on a voxel basis. This has the potential to be used to guide human-in-the-loop feedback to improve segmentations in clinical settings.

Numerous deep learning-based solutions have been proposed for histopathological image analysis over the past years. While they usually demonstrate exceptionally high accuracy, one key question is whether their precision might be affected by low-level image properties not related to histopathology but caused by microscopy image handling and pre-processing. In this paper, we analyze a popular NCT-CRC-HE-100K colorectal cancer dataset used in numerous prior works and show that both this dataset and the obtained results may be affected by data-specific biases. The most prominent revealed dataset issues are inappropriate color normalization, severe JPEG artifacts inconsistent between different classes, and completely corrupted tissue samples resulting from incorrect image dynamic range handling. We show that even the simplest model using only 3 features per image (red, green and blue color intensities) can demonstrate over 50% accuracy on this 9-class dataset, while using color histogram not explicitly capturing cell morphology features yields over 82% accuracy. Moreover, we show that a basic EfficientNet-B0 ImageNet pretrained model can achieve over 97.7% accuracy on this dataset, outperforming all previously proposed solutions developed for this task, including dedicated foundation histopathological models and large cell morphology-aware neural networks. The NCT-CRC-HE dataset is publicly available and can be freely used to replicate the presented results. The codes and pre-trained models used in this paper are available at https://github.com/gmalivenko/NCT-CRC-HE-experiments

Pathologists often classify various kidney diseases on the basis of visual assessments of biopsies from patients' kidneys; however, machine learning has the potential to automate and augment the accuracy of classifications. In one study, a team led by Pinaki Sarder, PhD and Brandon Ginley, BS (Jacobs School of Medicine and Biomedical Sciences at the University at Buffalo) developed a computational algorithm to detect the severity of diabetic kidney disease without human intervention. The algorithm examines a digital image of a patient's kidney biopsy at the microscopic level and extracts information on glomeruli, the small blood vessels of the kidney that filter waste from the blood for excretion. These structures are known to become progressively damaged and scarred over the course of diabetes. There are typically 10 to 20 individual glomeruli per biopsy, and the algorithm detects the location of each glomerular sub-component in the digital images, and then makes many measurements on each sub-component.

Two new studies reveal that modern machine learning--a branch of artificial intelligence in which systems learn from data, identify patterns, and make decisions--may augment traditional diagnostics of kidney disease. The findings appear in an upcoming issue of JASN. Pathologists often classify various kidney diseases on the basis of visual assessments of biopsies from patients' kidneys; however, machine learning has the potential to automate and augment the accuracy of classifications. In one study, a team led by Pinaki Sarder, PhD and Brandon Ginley, BS (Jacobs School of Medicine and Biomedical Sciences at the University at Buffalo) developed a computational algorithm to detect the severity of diabetic kidney disease without human intervention. The algorithm examines a digital image of a patient's kidney biopsy at the microscopic level and extracts information on glomeruli, the small blood vessels of the kidney that filter waste from the blood for excretion.